© 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. 19-TRANSCODER-HP
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    public domain

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makt
    -0.27
    alles
    -0.26
    UGIN
    -0.26
    辨åĪ«
    -0.26
    лег
    -0.25
    castle
    -0.25
    ader
    -0.25
    ç»ĻæĤ¨
    -0.24
     TG
    -0.24
    ä¼łçľŁ
    -0.24
    POSITIVE LOGITS
    ä¸Ģå®ļ
    0.28
    iom
    0.28
    åĩºéģĵ
    0.25
    ãĤ¹ãĤ¿
    0.25
    æľĿ
    0.25
    .newaxis
    0.25
    ảo
    0.24
    isex
    0.24
    oste
    0.23
    çĽ¸å¯¹è¾ĥ
    0.23
    Activations Density 0.012%

    No Known Activations