© 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. 18275
    Prev
    Next
    INDEX
    Explanations

    period

    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
    Can
    -0.30
    ,Q
    -0.30
    _qos
    -0.29
     Can
    -0.28
     can
    -0.27
    /Q
    -0.27
    phalt
    -0.27
     Q
    -0.26
    _can
    -0.26
    .Q
    -0.26
    POSITIVE LOGITS
     which
    0.51
    åĵª
    0.48
    which
    0.47
     Which
    0.45
    åĵªä¸ª
    0.44
    åĵªä¸Ģ个
    0.43
    Which
    0.41
     коÑĤоÑĢÑĭй
    0.37
     коÑĤоÑĢого
    0.36
    åĵªäºĽ
    0.35
    Activations Density 0.088%

    No Known Activations