© 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. 142166
    Prev
    Next
    INDEX
    Explanations

    Numerical/data processing

    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
     décou
    -0.24
    _REFER
    -0.24
    bourg
    -0.24
    å¦Ĥæŀľä¸įæĺ¯
    -0.23
    æ³Ħ
    -0.23
    {s
    -0.23
    .putString
    -0.23
    禧
    -0.23
    ä¹ŁçŁ¥éģĵ
    -0.23
    wing
    -0.23
    POSITIVE LOGITS
     NIL
    0.29
     essentially
    0.29
     negligible
    0.28
     equivalent
    0.27
    ognito
    0.27
     Pret
    0.27
     simpl
    0.27
    implicit
    0.26
    oger
    0.26
    invisible
    0.25
    Activations Density 14.758%

    No Known Activations