© 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. 31-TRANSCODER-HP
    7. 19532
    Prev
    Next
    INDEX
    Explanations

    formal documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è®°
    -0.29
    åľ¨åĮĹ京
    -0.29
    atta
    -0.28
     california
    -0.27
     gul
    -0.26
    crawl
    -0.26
    游
    -0.26
    reas
    -0.25
     march
    -0.25
    ç½®
    -0.25
    POSITIVE LOGITS
     AppModule
    0.26
     Crazy
    0.26
    izzes
    0.25
    licant
    0.25
    ç¾¤å²Ľ
    0.25
     voted
    0.24
    apot
    0.24
    ApplicationBuilder
    0.24
    ä¸ĥåįģ
    0.24
    shaw
    0.24
    Activations Density 0.045%

    No Known Activations