© 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. 21653
    Prev
    Next
    INDEX
    Explanations

    legal and code boilerplate

    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
    ###
    -0.09
    ####
    -0.09
     ###
    -0.08
    æŶéĹ´éĩĮ
    -0.08
    č↵č↵č↵
    -0.07
    rine
    -0.07
    _JOIN
    -0.07
    arine
    -0.07
     ####
    -0.07
    ##
    -0.07
    POSITIVE LOGITS
    ç¥ĿæĤ¨
    0.07
    оÑĢоÑĤ
    0.07
    çŀ³
    0.07
    </think>
    0.07
    tribu
    0.07
    åľ¨åħ¶ä¸Ń
    0.07
     repu
    0.07
    rotch
    0.07
    éĢļè¿ĩåĪĨæŀIJ
    0.07
    chie
    0.07
    Activations Density 0.783%

    No Known Activations