© 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. 31-TRANSCODER-HP
    7. 17985
    Prev
    Next
    INDEX
    Explanations

    truncated word 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
    Negative Logits
     CHIP
    -0.28
    icha
    -0.27
    åħħåĪĨ
    -0.25
     Drops
    -0.24
    ilot
    -0.24
     Lebanese
    -0.24
    ambia
    -0.24
    便äºİ
    -0.23
    CHIP
    -0.23
    ismet
    -0.23
    POSITIVE LOGITS
    azi
    0.28
    cem
    0.27
    paged
    0.27
    nu
    0.27
    AZ
    0.26
     ton
    0.26
    _caps
    0.25
    æŁ°
    0.25
     nu
    0.25
     Pall
    0.24
    Activations Density 0.101%

    No Known Activations