© 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. 19412
    Prev
    Next
    INDEX
    Explanations

    number of instances

    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
    à¸Ĥาà¸Ķ
    -0.07
    æļĤæŶ
    -0.06
    effectu
    -0.06
    æĸ°æĿIJæĸĻæľīéĻIJåħ¬åı¸
    -0.06
    æĺİçŁ¥
    -0.06
     temporarily
    -0.06
    _defaults
    -0.06
    ä¸ĢæŶ
    -0.06
    å°½æľī
    -0.06
    .vel
    -0.06
    POSITIVE LOGITS
    inst
    0.05
     elim
    0.05
    ÑıÑģ
    0.05
    âĪĴ
    0.05
    -
    0.05
    Inst
    0.05
    cko
    0.05
    æ¸ħé¦Ļ
    0.05
     Inst
    0.05
    гам
    0.04
    Activations Density 0.037%

    No Known Activations