© 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. 58379
    Prev
    Next
    INDEX
    Explanations

    code tokens

    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
    SWG
    -0.29
    otre
    -0.27
    æīĵéĢłæĪIJ
    -0.26
     Maur
    -0.25
    ×Ļ×Ķ
    -0.25
     expected
    -0.25
    éĢĢç¨İ
    -0.25
    èĦ«
    -0.25
    人æ°ijæľįåĬ¡
    -0.25
    åIJįçīĩ
    -0.24
    POSITIVE LOGITS
    tim
    0.30
    æ´ŀ
    0.30
    Tim
    0.30
     tim
    0.29
    aju
    0.27
    olatile
    0.27
    acie
    0.26
    _tim
    0.26
    ä½ĵ
    0.26
    .tim
    0.25
    Activations Density 0.000%

    No Known Activations