© 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. 108553
    Prev
    Next
    INDEX
    Explanations

    9

    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
    磶
    -0.30
    æĬĢæľ¯åĪĽæĸ°
    -0.29
    zer
    -0.28
    emie
    -0.26
    soever
    -0.26
    йÑĤе
    -0.26
    ubb
    -0.25
    tie
    -0.25
    tti
    -0.25
    baugh
    -0.25
    POSITIVE LOGITS
     bulls
    0.28
    çīĪæĿĥ声æĺİ
    0.28
    flix
    0.28
     lá»ĭch
    0.26
    ä¸ĥæĺŁ
    0.26
    indr
    0.25
    æ¦Ĥ
    0.25
     kurs
    0.25
    æ¦Ĥè¿°
    0.24
     Lud
    0.24
    Activations Density 0.892%

    No Known Activations