© 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. 27-TRANSCODER-HP
    7. 7830
    Prev
    Next
    INDEX
    Explanations

    words start with "su"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    chio
    -0.28
     eleg
    -0.28
    asis
    -0.28
    æĹģ
    -0.27
    éī´
    -0.27
    å¼¯æĽ²
    -0.25
     quil
    -0.25
    ç¼ĸ
    -0.25
     smack
    -0.25
     sack
    -0.24
    POSITIVE LOGITS
    pe
    0.27
    PE
    0.26
    驽
    0.26
    addin
    0.25
    ham
    0.24
    ape
    0.24
    ope
    0.24
     booze
    0.24
    Ľå»º
    0.24
    +xml
    0.24
    Activations Density 0.016%

    No Known Activations