© 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. 19215
    Prev
    Next
    INDEX
    Explanations

    the

    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
    è½»
    -0.38
    è¼ķ
    -0.35
    _Internal
    -0.28
     nhẹ
    -0.28
     Issues
    -0.27
    ternal
    -0.27
    Issues
    -0.27
     trail
    -0.27
     lightly
    -0.27
     Liberal
    -0.27
    POSITIVE LOGITS
     condition
    0.46
     Condition
    0.43
    Condition
    0.39
    condition
    0.38
    .condition
    0.31
     conditions
    0.30
    _condition
    0.30
    æĿ¡ä»¶
    0.30
     ÑĥÑģлов
    0.29
     problem
    0.29
    Activations Density 0.600%

    No Known Activations