© 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. 32-TRANSCODER-HP
    7. 41730
    Prev
    Next
    INDEX
    Explanations

    file conversions and editors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĤол
    -0.25
    èĿ¼
    -0.25
    .Gen
    -0.25
    ftype
    -0.25
     til
    -0.25
    èħ¾
    -0.25
    毯
    -0.24
    èĥ¶
    -0.24
    ins
    -0.24
    -caret
    -0.24
    POSITIVE LOGITS
     pharm
    0.29
    opia
    0.28
     organization
    0.26
    stuff
    0.26
    aph
    0.25
    eman
    0.25
    man
    0.25
    chemy
    0.25
     organ
    0.24
    polation
    0.24
    Activations Density 0.006%

    No Known Activations