© 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. 12-TRANSCODER-HP
    7. 23498
    Prev
    Next
    INDEX
    Explanations

    general discussions/opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    spaces
    -0.31
    space
    -0.28
    yx
    -0.28
    vements
    -0.27
    reate
    -0.26
    åŁĿ
    -0.26
    æĻļ
    -0.26
    ways
    -0.25
    hcp
    -0.25
    åıijè¡Į
    -0.25
    POSITIVE LOGITS
    JsonValue
    0.28
     ::::::::
    0.26
    é«»
    0.26
    ylv
    0.26
    ä¿Ŀä¿®
    0.25
    åĦ¿
    0.24
     Judiciary
    0.24
    åħĴ
    0.24
     Shader
    0.23
    Accent
    0.23
    Activations Density 0.005%

    No Known Activations