© 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. 31-TRANSCODER-HP
    7. 18969
    Prev
    Next
    INDEX
    Explanations

    Formal contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ael
    -0.29
    åij¼åı«
    -0.28
     emot
    -0.26
     dip
    -0.25
     azimuth
    -0.25
    .report
    -0.25
    trys
    -0.24
    æĸ°éĹ»è®°èĢħ
    -0.24
    ais
    -0.24
    chars
    -0.24
    POSITIVE LOGITS
    retval
    0.30
    æļĤç¼ĵ
    0.28
    intern
    0.27
    isAdmin
    0.26
    |$
    0.26
    (retval
    0.26
     Junior
    0.26
    ITS
    0.26
    Networking
    0.26
    ownt
    0.25
    Activations Density 3.311%

    No Known Activations