© 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. 12-TRANSCODER-HP
    7. 23096
    Prev
    Next
    INDEX
    Explanations

    Different subjects

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -0.27
    ty
    -0.26
    /pay
    -0.26
    è°IJ
    -0.25
    tingham
    -0.25
     Autos
    -0.25
    plier
    -0.25
    éĨĽ
    -0.24
    ELL
    -0.24
    æĺ¼å¤ľ
    -0.24
    POSITIVE LOGITS
    çŀ¬
    0.28
    è¾ħ导åijĺ
    0.27
    _dicts
    0.25
     reason
    0.25
    带走
    0.25
    à´·
    0.25
     formations
    0.24
    quÃŃ
    0.24
    weg
    0.24
     literals
    0.24
    Activations Density 0.000%

    No Known Activations