© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 85317
    Prev
    Next
    INDEX
    Explanations

    Code/Documentation

    np_max-act · gemini-2.0-flash
    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
    毛巾
    -0.07
     Niet
    -0.07
     trous
    -0.06
     complain
    -0.06
    slot
    -0.06
    ильно
    -0.06
     cô
    -0.06
    瞧
    -0.06
     expertise
    -0.06
    帅哥
    -0.06
    POSITIVE LOGITS
     TYPO
    0.07
     (()
    0.07
    Anything
    0.06
     __________________
    0.06
    -touch
    0.06
    ᄀ
    0.06
     Contin
    0.06
     منذ
    0.06
    _anim
    0.06
    ✭
    0.06
    Activations Density 0.063%

    No Known Activations