© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 8639
    Prev
    Next
    INDEX
    Explanations

    .h files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yourselves
    -0.08
    æĬķ稿éĤ®ç®±
    -0.08
    欢è¿İ广大
    -0.07
    ayscale
    -0.07
    请èģĶç³»æĪij们åĪłéĻ¤
    -0.07
     geho
    -0.07
    天çĽĸ
    -0.07
    .FileNotFoundException
    -0.07
    æŀľ
    -0.07
     filiale
    -0.07
    POSITIVE LOGITS
    _CLIP
    0.07
    ably
    0.06
     avanc
    0.06
    æľī家
    0.06
    ieg
    0.06
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    0.06
    ssi
    0.06
    omi
    0.06
    à¹Īà¸Ńà¸ĩ
    0.06
     Jonas
    0.06
    Activations Density 0.034%

    No Known Activations