© 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. 108217
    Prev
    Next
    INDEX
    Explanations

    lessons

    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
    ä¸Ģ个æĸ°çļĦ
    -0.29
    ä¸įä¿¡
    -0.27
    æĽĿåħī
    -0.26
    aper
    -0.26
    伯
    -0.26
    frag
    -0.25
     bitten
    -0.24
    ÅĤó
    -0.24
    วà¸Ļ
    -0.24
    łģ
    -0.24
    POSITIVE LOGITS
     rejo
    0.28
    DSA
    0.25
     progress
    0.25
     synthes
    0.25
     progression
    0.24
    wel
    0.24
     elo
    0.24
     Mint
    0.24
     Asi
    0.24
     regul
    0.24
    Activations Density 0.141%

    No Known Activations