© 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. 43139
    Prev
    Next
    INDEX
    Explanations

    Code/hyphenated text

    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
    ;&#
    -0.31
    ::.
    -0.29
    ï¼ĮãĢĬ
    -0.29
    %.↵↵
    -0.28
    .="
    -0.27
    __()↵↵
    -0.27
    ().↵
    -0.26
    “(
    -0.26
    ;a
    -0.26
     .↵↵
    -0.26
    POSITIVE LOGITS
    è°Ĵ
    0.29
     minus
    0.26
     relates
    0.25
    лиÑĤ
    0.24
    è¦ģ注æĦı
    0.24
     hend
    0.24
    resent
    0.24
    0.24
    Ø·ÙĬع
    0.23
    _IDENTIFIER
    0.23
    Activations Density 0.011%

    No Known Activations