© 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. 11-RESID-POST-AA
    6. 40687
    Prev
    Next
    INDEX
    Explanations

    ana

    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
     checks
    -0.07
    Ў
    -0.07
    ern
    -0.06
    transform
    -0.06
     yaz
    -0.06
    Try
    -0.06
     Returns
    -0.06
    calc
    -0.06
    .Priority
    -0.06
     bk
    -0.06
    POSITIVE LOGITS
    ucus
    0.07
     acidic
    0.07
    𒀸
    0.07
    跳舞
    0.07
     ARC
    0.07
     CONSTANTS
    0.06
    /Math
    0.06
     Messiah
    0.06
    侏
    0.06
    _DEPEND
    0.06
    Activations Density 0.001%

    No Known Activations