© 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. 35-TRANSCODER-HP
    7. 40661
    Prev
    Next
    INDEX
    Explanations

    technical/specialized vocabulary

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     clearly
    -0.27
    æľĿ
    -0.27
    _FORWARD
    -0.25
    oux
    -0.25
     blockDim
    -0.25
    æ¶Ĥ
    -0.25
    ãģĭãģĭãĤĬ
    -0.25
     diets
    -0.25
     зав
    -0.25
     uphill
    -0.24
    POSITIVE LOGITS
     infer
    0.28
    iglia
    0.27
    antry
    0.27
    æĦıå¤ĸ
    0.26
     fend
    0.25
    ses
    0.25
    spi
    0.25
    sorting
    0.25
    åľ¨å¤ĸéĿ¢
    0.25
    /xhtml
    0.24
    Activations Density 55.998%

    No Known Activations