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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129947
    Prev
    Next
    INDEX
    Explanations

    ASTE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èµ°å¾Ĺ
    -0.28
    NIL
    -0.27
     Grü
    -0.27
     Powell
    -0.27
    yal
    -0.26
     Allies
    -0.25
     NIL
    -0.24
    ÑģилÑĮ
    -0.24
    AUD
    -0.24
    adh
    -0.24
    POSITIVE LOGITS
    0.27
    âĢĸ
    0.26
     amo
    0.26
    \n
    0.25
     strokes
    0.24
    é¡
    0.24
    äºĨèµ·æĿ¥
    0.24
     accordingly
    0.24
     him
    0.24
    âĢ
    0.24
    Activations Density 0.008%

    No Known Activations