© 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. 25-TRANSCODER-HP
    7. 108203
    Prev
    Next
    INDEX
    Explanations

    programming related questions/titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lie
    -0.26
    lor
    -0.25
    ahead
    -0.25
    .future
    -0.25
    ault
    -0.25
    charging
    -0.24
    æĿ¾å¼Ľ
    -0.24
     Ajax
    -0.24
     Pride
    -0.23
    ophil
    -0.23
    POSITIVE LOGITS
    obar
    0.31
    yny
    0.29
    æĪª
    0.28
    ibbon
    0.27
     negatives
    0.26
     comercial
    0.25
    fur
    0.25
    bff
    0.24
     upro
    0.24
    å§Ĭ妹
    0.24
    Activations Density 0.942%

    No Known Activations