© 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. 19-TRANSCODER-HP
    7. 8527
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hek
    -0.28
    jected
    -0.26
     Burn
    -0.25
     Buckley
    -0.25
    bm
    -0.24
     Carn
    -0.24
    ))->
    -0.23
    éĤ£äºĽ
    -0.23
    itecture
    -0.23
    éij
    -0.23
    POSITIVE LOGITS
    ä¸ĭè¾¾
    0.28
    ç»Ĩå¿ĥ
    0.28
    esser
    0.27
    ä½Ľ
    0.26
     tastes
    0.25
     taste
    0.24
    该游æĪı
    0.24
    说æĺ¯
    0.24
    ç¬ijç¬ij
    0.24
    éĹ®é¢ĺæĺ¯
    0.23
    Activations Density 0.033%

    No Known Activations