© 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. 20-TRANSCODER-HP
    7. 142175
    Prev
    Next
    INDEX
    Explanations

    math, code, equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .te
    -0.27
    åĬĽéĩı
    -0.27
    -label
    -0.26
     label
    -0.26
    .AutoScaleMode
    -0.26
    æĮĩ导ä¸ĭ
    -0.26
    èģĮ
    -0.25
    è°¥
    -0.25
    æ³¢
    -0.25
    False
    -0.25
    POSITIVE LOGITS
    skin
    0.28
     reels
    0.27
    ORAGE
    0.26
    éķ¿çŁŃ
    0.26
    .SOCK
    0.25
    Fair
    0.25
    aget
    0.25
    æĥħ人
    0.25
    bounded
    0.25
    OTE
    0.25
    Activations Density 13.837%

    No Known Activations