© 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. 19046
    Prev
    Next
    INDEX
    Explanations

    API keys and tokens

    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
    æ»ĵ
    -0.08
    æĤ¨çļĦè¯Ħ论
    -0.07
    umon
    -0.07
    ä»ij
    -0.07
    icine
    -0.07
    agi
    -0.07
    ORI
    -0.07
    å¤ĩå¿ĺ
    -0.07
    apura
    -0.07
    å¾Ĺåħ¶
    -0.07
    POSITIVE LOGITS
    ç®ĹäºĨ
    0.07
    rek
    0.07
    çĩ
    0.06
    éŀł
    0.06
    Ïģαν
    0.06
     random
    0.06
    nces
    0.06
    éĤ£ä¸įæĺ¯
    0.06
    warts
    0.06
    ndon
    0.06
    Activations Density 0.046%

    No Known Activations