© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39781
    Prev
    Next
    INDEX
    Explanations

    . and digits

    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
    adian
    -0.07
    <|im_start|>
    -0.06
    äººä¹Ł
    -0.06
     dÆ°
    -0.06
    è¿ŀæİ¥æľī
    -0.06
    æĭįåĩº
    -0.06
    çĽ¸ä¼¼æĸĩçĮ®
    -0.06
    æľ¬ç½ij
    -0.06
    éļħ
    -0.06
    antas
    -0.06
    POSITIVE LOGITS
    è§Ħ
    0.07
    enf
    0.07
    æī¿
    0.07
     Atta
    0.07
     asp
    0.07
    uchos
    0.07
    天èĬ±
    0.06
     pedest
    0.06
    иÑĢо
    0.06
    ÑĢев
    0.06
    Activations Density 0.013%

    No Known Activations