© 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. 31-TRANSCODER-HP
    7. 18815
    Prev
    Next
    INDEX
    Explanations

    related to attention

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å¼ĢäºĨ
    -0.27
     embell
    -0.27
    éķ¿çĽ¸
    -0.26
     templ
    -0.26
    venes
    -0.25
    æĸ°ä¸ī
    -0.25
     orth
    -0.25
    :message
    -0.25
    orth
    -0.24
    cura
    -0.24
    POSITIVE LOGITS
    emain
    0.28
    Give
    0.27
     give
    0.27
    дин
    0.27
    _SIGNATURE
    0.26
     given
    0.25
    éĽĨä¸Ń
    0.25
    Moment
    0.25
    _pay
    0.25
    cit
    0.25
    Activations Density 0.033%

    No Known Activations