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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15-RESID-POST-AA
    11. 78118
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sor
    -0.07
    mong
    -0.07
    قي
    -0.07
    Lite
    -0.07
    棍
    -0.07
     bọn
    -0.06
    tc
    -0.06
    LDAP
    -0.06
     البط
    -0.06
    --;
↵
    -0.06
    POSITIVE LOGITS
    _placeholder
    0.08
    пресс
    0.07
    如果您
    0.07
    _ub
    0.07
    -you
    0.07
    .anchor
    0.07
    (storage
    0.07
    獎
    0.07
     occupants
    0.07
    -now
    0.07
    Activations Density 0.005%

    No Known Activations