© 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. 108636
    Prev
    Next
    INDEX
    Explanations

    Names and books

    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
     Pew
    -0.28
    coon
    -0.27
     peeled
    -0.26
    åĨħ饰
    -0.26
    asics
    -0.24
    abin
    -0.23
    webtoken
    -0.23
    è¶ħé¢Ŀ
    -0.23
     Emblem
    -0.23
    inski
    -0.23
    POSITIVE LOGITS
    åľ¨ç½ij绾
    0.26
    æĪIJåIJį
    0.25
    rection
    0.25
    изаÑĨиÑı
    0.24
     revision
    0.24
     Southampton
    0.24
    è°ĭ
    0.23
     lider
    0.23
    lam
    0.23
    {@
    0.23
    Activations Density 0.895%

    No Known Activations