© 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. 111451
    Prev
    Next
    INDEX
    Explanations

    Informal online discussions/questions

    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
     stamp
    -0.26
    èĢĮè¿Ļ
    -0.26
    纵横
    -0.26
    lox
    -0.26
    罪
    -0.25
     Guards
    -0.25
    .GetAll
    -0.25
    縱
    -0.25
    踮
    -0.25
    èĵī
    -0.25
    POSITIVE LOGITS
     diet
    0.29
    EFF
    0.27
    icture
    0.26
     kidding
    0.26
    HELL
    0.25
     diets
    0.25
     Vik
    0.25
    èĹģ
    0.24
    quals
    0.24
    .Diagnostics
    0.24
    Activations Density 0.018%

    No Known Activations