© 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. 111544
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    porter
    -0.27
    æĸĹ
    -0.26
    .tpl
    -0.26
     DECLARE
    -0.25
    shr
    -0.25
    eros
    -0.25
    åĭĥ
    -0.25
    tests
    -0.24
    -tests
    -0.24
    usk
    -0.24
    POSITIVE LOGITS
    ingly
    0.29
    licted
    0.24
    ãĥªãĥ³ãĤ°
    0.24
    åħ¨é¢Ŀ
    0.24
    IP
    0.23
    è°ģçŁ¥
    0.23
    à¹Ģà¸ĭล
    0.23
    æľīåħ³éĥ¨éŨ
    0.23
    ipse
    0.23
     plast
    0.23
    Activations Density 0.020%

    No Known Activations

    This feature has no known activations.