© 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. 29061
    Prev
    Next
    INDEX
    Explanations

    shows his frustration

    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
    WAYS
    -0.08
    æľĢåIJİæĺ¯
    -0.08
    çķĮ
    -0.07
    ож
    -0.06
    ä½Ĩæľī
    -0.06
    éĥ¨ä¸»ä»»
    -0.06
    datatype
    -0.06
    第äºĮ人æ°ijåĮ»éĻ¢
    -0.06
    éĢ¼
    -0.06
     наÑĢ
    -0.06
    POSITIVE LOGITS
    abbr
    0.08
    篤
    0.08
    baran
    0.07
    lager
    0.07
    æĮ¯åįİ
    0.07
    addir
    0.07
    ited
    0.07
    ç¬ĥ
    0.06
    _BINDING
    0.06
    æijĩæijĩ
    0.06
    Activations Density 0.155%

    No Known Activations