© 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. 98516
    Prev
    Next
    INDEX
    Explanations

    code

    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
    +='
    -0.29
     "+"
    -0.28
    æİĪ
    -0.26
    atories
    -0.26
    +="
    -0.25
    *out
    -0.24
    æĤ´
    -0.24
     '+'
    -0.24
    Extension
    -0.24
    atég
    -0.24
    POSITIVE LOGITS
    æĺ¯ä¸ŃåĽ½
    0.28
     plates
    0.26
    è½Ń
    0.25
    ä¸įåľ¨ä¹İ
    0.25
    ä¸Ĭå¸Ĥ
    0.25
    Äħż
    0.24
    åľ¨ä¹İ
    0.24
    襻
    0.24
     Constit
    0.24
    æľ¬ç½ijç«Ļ
    0.24
    Activations Density 0.034%

    No Known Activations