© 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. 8140
    Prev
    Next
    INDEX
    Explanations

    replace

    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
    ByVersion
    -0.27
    áb
    -0.26
    ascus
    -0.24
    VEC
    -0.24
    comed
    -0.24
    å¹´ä¹ĭ
    -0.23
    berry
    -0.23
    åĽłä¸ºæĪij
    -0.23
    æ³³
    -0.23
     lod
    -0.23
    POSITIVE LOGITS
    end
    0.25
    Exact
    0.25
     vague
    0.24
    çļĦä¸Ģéĥ¨åĪĨ
    0.24
    ä»ħä¾Ľ
    0.24
     thesis
    0.24
    umann
    0.24
    模ç³Ĭ
    0.23
    xcd
    0.23
    äºİæĺ¯
    0.23
    Activations Density 0.109%

    No Known Activations