© 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. 7896
    Prev
    Next
    INDEX
    Explanations

    code and technical documents

    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
     fluent
    -0.30
    éĽĨä¸Ń
    -0.29
    åħ·ä½ĵæĥħåĨµ
    -0.28
    ç»ĻäºĨ
    -0.25
     multis
    -0.25
    åİŁæĿ¥æĺ¯
    -0.25
    lin
    -0.24
    _Begin
    -0.24
     intel
    -0.24
    常
    -0.23
    POSITIVE LOGITS
    ewood
    0.28
    оÑī
    0.26
    icago
    0.25
    hyp
    0.25
    esteem
    0.24
    fabric
    0.23
    룴
    0.23
    帻
    0.23
    comma
    0.23
    ¶Ī
    0.23
    Activations Density 0.018%

    No Known Activations