© 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. 32-TRANSCODER-HP
    7. 43527
    Prev
    Next
    INDEX
    Explanations

    obstructions or limitations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    缺失
    -0.29
     positioning
    -0.28
     fading
    -0.28
    unting
    -0.27
     missing
    -0.27
    moth
    -0.27
     choking
    -0.27
     trailing
    -0.26
     organizing
    -0.26
    ä¸Ĭæĺł
    -0.26
    POSITIVE LOGITS
     pass
    0.32
    ecast
    0.32
    pass
    0.31
    ware
    0.29
    Pass
    0.28
    ullo
    0.28
     comb
    0.27
    _pass
    0.27
     Pass
    0.26
    ICATION
    0.26
    Activations Density 0.001%

    No Known Activations