© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22009
    Prev
    Next
    INDEX
    Explanations

    enumerating types, categories, questions, steps, measures

    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
    åŃĺçļĦ
    -0.06
    ä»·çļĦ
    -0.06
    ä»ĸ身ä¸Ĭ
    -0.06
    _custom
    -0.06
    umer
    -0.06
    ritos
    -0.06
    æĺıè¿·
    -0.06
    _hook
    -0.06
    ä¸Ĭä¸į
    -0.06
     Cra
    -0.05
    POSITIVE LOGITS
    ulture
    0.06
    ä¸įåĪĨ
    0.05
    æºľ
    0.05
    æĹ¢
    0.05
    ìľł
    0.05
    кÑĥп
    0.05
    æĹ¢æľī
    0.05
    å¼łé£ŀ
    0.05
    oleÄį
    0.05
    ilu
    0.05
    Activations Density 0.085%

    No Known Activations