© 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. 40772
    Prev
    Next
    INDEX
    Explanations

    creation or comments

    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
    utores
    -0.07
    æ»
    -0.07
    illés
    -0.07
    tracked
    -0.06
    亳
    -0.06
    ÑĥÑģа
    -0.06
    æĻ®éĢļçļĦ
    -0.06
    éģµ
    -0.06
    åıªèĥ½æĺ¯
    -0.06
    attendance
    -0.06
    POSITIVE LOGITS
    ivid
    0.08
    rie
    0.07
    解éĩĬ说
    0.07
    å·²éĢļè¿ĩ
    0.07
    æĬĬå®ĥ们
    0.07
    agian
    0.07
     hypoc
    0.07
    åı¦
    0.07
     Kalt
    0.07
    羣æĺ¯ä¸ª
    0.06
    Activations Density 0.003%

    No Known Activations