© 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. 18882
    Prev
    Next
    INDEX
    Explanations

    body

    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
    pone
    -0.29
    çļĦæŃ¥ä¼IJ
    -0.26
    ä½ĵè´¨
    -0.26
    çļĦæķĻåѦ
    -0.26
    line
    -0.26
    oked
    -0.25
    .getLine
    -0.25
    æī¼
    -0.24
     line
    -0.24
     Line
    -0.24
    POSITIVE LOGITS
     paragraphs
    0.33
     paragraph
    0.33
    ela
    0.32
    oron
    0.30
    eron
    0.29
     section
    0.27
    uela
    0.27
    keh
    0.27
     part
    0.27
    airy
    0.27
    Activations Density 0.024%

    No Known Activations