© 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. 27-TRANSCODER-HP
    7. 8976
    Prev
    Next
    INDEX
    Explanations

    non-English, code, and legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     partida
    -0.28
    è¾ħ
    -0.28
    è°ĵ
    -0.27
    å®ľ
    -0.26
     partie
    -0.26
    æİ¢
    -0.24
    SELL
    -0.24
    æŶå°ļ
    -0.24
     sp
    -0.24
    <IM
    -0.24
    POSITIVE LOGITS
    ointed
    0.30
    ponsors
    0.27
    å¾Ļ
    0.26
    åĢ¡è®®
    0.26
    endo
    0.25
    ycop
    0.24
     prio
    0.24
    nist
    0.24
    éĻ¢éĻ¢éķ¿
    0.24
    éħįåģ¶
    0.24
    Activations Density 0.001%

    No Known Activations