© 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. 108427
    Prev
    Next
    INDEX
    Explanations

    Code and foreign languages

    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¿Ŀéļľ
    -0.28
    çļĦéĤ£ç§į
    -0.28
     Mot
    -0.27
    çºł
    -0.26
    çĶ·å¥³
    -0.26
     Commission
    -0.26
     mot
    -0.25
    è°
    -0.25
    身
    -0.24
    agento
    -0.24
    POSITIVE LOGITS
    дей
    0.29
    zenia
    0.29
    á»ĵi
    0.28
    ptest
    0.25
    suit
    0.24
    andan
    0.24
    è±³
    0.24
     scratched
    0.23
    __(*
    0.23
     Tribune
    0.23
    Activations Density 1.050%

    No Known Activations