© 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. 19270
    Prev
    Next
    INDEX
    Explanations

    formal document terms

    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
    jo
    -0.29
    orts
    -0.27
    ort
    -0.26
    orse
    -0.25
    DI
    -0.24
     paraph
    -0.24
    \Collection
    -0.24
    Extern
    -0.24
    io
    -0.24
    ãĤ£
    -0.24
    POSITIVE LOGITS
    /inc
    0.27
    è½½
    0.26
     INC
    0.25
     TypeName
    0.25
    comma
    0.25
     healed
    0.24
    è®Ń
    0.24
     ÐŁÐµÑĤÑĢ
    0.23
    缸è¾ĥ
    0.23
     quant
    0.23
    Activations Density 1.906%

    No Known Activations