© 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. 24-TRANSCODER-HP
    7. 150033
    Prev
    Next
    INDEX
    Explanations

    article text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Olympic
    -0.34
     Bowl
    -0.32
     offseason
    -0.31
    kle
    -0.31
    çİĭæľĿ
    -0.29
     athlete
    -0.29
     bowl
    -0.28
    æĶ¾åģĩ
    -0.28
    çIJĥåijĺ
    -0.28
     athletes
    -0.28
    POSITIVE LOGITS
    æ¶ĪéĻ¤
    0.28
    $password
    0.25
    thro
    0.25
     Mattis
    0.24
    arus
    0.24
    æĪĺåľº
    0.24
     skew
    0.23
    uyá»ĩn
    0.23
    æ¯Ķè¾ĥé«ĺ
    0.23
     assigning
    0.23
    Activations Density 1.059%

    No Known Activations