© 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. 58378
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
    sWith
    -0.36
    illery
    -0.25
    swith
    -0.25
    -collar
    -0.25
    aphrag
    -0.25
    atron
    -0.25
    éĺ³åı°
    -0.24
    .cloudflare
    -0.24
    atre
    -0.24
    .fm
    -0.24
    POSITIVE LOGITS
    antage
    0.27
    åīįè¾Ī
    0.25
    å±ķå¼Ģ
    0.25
    éĹª
    0.25
     results
    0.25
     wel
    0.24
    黳
    0.24
    罪
    0.24
    big
    0.24
    ENTE
    0.23
    Activations Density 0.002%

    No Known Activations