© 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. 22-TRANSCODER-HP
    7. 129784
    Prev
    Next
    INDEX
    Explanations

    fantasy franchises

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SWG
    -0.30
    ä¸į稳å®ļ
    -0.27
    Ñģке
    -0.27
    anked
    -0.26
    缩
    -0.25
    abcdefghijkl
    -0.24
    çī¹æľĹ
    -0.24
    StatusLabel
    -0.24
    onacci
    -0.24
    åĪĨåĮĸ
    -0.24
    POSITIVE LOGITS
    æĺ¯éĿŀ
    0.27
    è¿Ļ个游æĪı
    0.26
     Lantern
    0.26
     guts
    0.25
     Ventures
    0.25
    vent
    0.25
    æĨ¬
    0.25
     inund
    0.25
     vests
    0.24
    åIJ¯ç¤º
    0.24
    Activations Density 0.015%

    No Known Activations