© 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. 19-RESID-POST-AA
    6. 76610
    Prev
    Next
    INDEX
    Explanations

    descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ра�
    -0.07
    mares
    -0.07
    _AV
    -0.07
     vej
    -0.07
    лер
    -0.07
    idle
    -0.07
    Apr
    -0.06
    娃
    -0.06
    要知道
    -0.06
    Pg
    -0.06
    POSITIVE LOGITS
     orchestra
    0.08
    隐约
    0.07
     Casting
    0.07
    ốc
    0.06
     actionBar
    0.06
     playground
    0.06
    reader
    0.06
    _array
    0.06
     cluster
    0.06
     meticulously
    0.06
    Activations Density 0.018%

    No Known Activations