© 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. 35-TRANSCODER-HP
    7. 39949
    Prev
    Next
    INDEX
    Explanations

    code & licenses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ih
    -0.29
    çļĦ羣å®ŀæĢ§
    -0.27
    rc
    -0.27
    èĪĨ
    -0.26
    iq
    -0.26
    第ä¸ĢæĿ¡
    -0.26
    tps
    -0.26
    iu
    -0.25
     },{↵
    -0.25
    uri
    -0.25
    POSITIVE LOGITS
     scramble
    0.28
    èIJ¥éĢłèī¯å¥½
    0.27
    è¿Ļ个è¯į
    0.25
    å¤ļæł·æĢ§
    0.25
    angement
    0.24
     cottage
    0.24
    æĻģ
    0.24
     goog
    0.23
     Promotion
    0.23
    emento
    0.23
    Activations Density 0.662%

    No Known Activations