© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 31203
    Prev
    Next
    INDEX
    Explanations

    Hook

    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_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
    _peer
    -0.08
    ACK
    -0.07
     ske
    -0.07
    .FETCH
    -0.07
    承接
    -0.07
     quar
    -0.07
    日凌晨
    -0.06
     peninsula
    -0.06
    覆盖
    -0.06
    ixels
    -0.06
    POSITIVE LOGITS
    StrictEqual
    0.08
     MB
    0.07
     +↵
    0.07
     Typ
    0.07
    初恋
    0.07
     +
    ↵
    0.06
    حزب
    0.06
    odu
    0.06
     introduces
    0.06
     asign
    0.06
    Activations Density 0.005%

    No Known Activations