© 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. 18-TRANSCODER-HP
    7. 89127
    Prev
    Next
    INDEX
    Explanations

    behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åıŁ
    -0.32
    غÙĦ
    -0.26
    ITTER
    -0.24
    ä¸Ģæł·
    -0.23
    论
    -0.23
    ivre
    -0.23
    æĺ¯åIJ¦åŃĺåľ¨
    -0.23
    تÙģ
    -0.23
     cut
    -0.22
     raz
    -0.22
    POSITIVE LOGITS
     [('
    0.26
    é£İæĥħ
    0.26
     requis
    0.26
    åĽ·
    0.25
    èĵ¬åĭĥ
    0.25
     nid
    0.24
    -strokes
    0.24
     <![
    0.24
    åĿļ
    0.24
     propulsion
    0.24
    Activations Density 2.857%

    No Known Activations