© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 130102
    Prev
    Next
    INDEX
    Explanations

    medical emergencies

    np_max-act · gemini-2.0-flash

    phrases giving emergency first‑aid or medical response instructions in safety/SDS-style text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    иш
    -0.07
     Boyd
    -0.07
    far
    -0.07
    ltk
    -0.07
    oit
    -0.07
    aps
    -0.06
     boxing
    -0.06
    ้อม
    -0.06
    ek
    -0.06
    Boost
    -0.06
    POSITIVE LOGITS
     Danger
    0.07
     revital
    0.07
    _MODAL
    0.07
    DefaultCloseOperation
    0.07
    def
    0.07
    低成本
    0.06
     realloc
    0.06
    _clone
    0.06
    Production
    0.06
    נחל
    0.06
    Activations Density 0.029%

    No Known Activations