© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 44110
    Prev
    Next
    INDEX
    Explanations

    Code and document titles

    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
    Negative Logits
    段
    -0.30
    åŁŁ
    -0.28
    æĵį
    -0.27
    ainties
    -0.26
    .toHexString
    -0.24
    éħ¸
    -0.24
     Hastings
    -0.24
    ivities
    -0.24
    pciones
    -0.24
    ecimal
    -0.24
    POSITIVE LOGITS
    ç¾ģ
    0.34
    ocker
    0.29
    noc
    0.26
    ew
    0.26
    n
    0.26
     dred
    0.25
    poser
    0.24
    æĹ¥æ¶Īæģ¯
    0.24
    fuse
    0.24
    inger
    0.23
    Activations Density 0.001%

    No Known Activations