© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20330
    Prev
    Next
    INDEX
    Explanations

    Prohibition, Hyperdrive, Marketing, Enough, Wrong, Machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uen
    -0.06
    æ±Ŀ
    -0.06
    æĽ²
    -0.06
    igd
    -0.06
    orre
    -0.06
    .Euler
    -0.06
    æĹ¥æĸ°æľĪ
    -0.06
    å¼ķ人åħ¥
    -0.06
    anima
    -0.06
    寿
    -0.05
    POSITIVE LOGITS
    ://"
    0.05
     near
    0.05
    ëĵł
    0.05
     Dict
    0.05
     consistent
    0.05
    wür
    0.05
    两éĥ¨åĪĨ
    0.05
    à¹ģà¸ģà¹Ī
    0.04
    <html
    0.04
    enez
    0.04
    Activations Density 0.064%

    No Known Activations