© 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. 63241
    Prev
    Next
    INDEX
    Explanations

    but be, get more

    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
    /tags
    -0.07
     appunto
    -0.07
    anton
    -0.07
    身ä¸Ĭä¸ĭ
    -0.07
    issue
    -0.07
    ä¿¡æģ¯åıĬ
    -0.07
    å·¥ç¨ĭåĴĮ
    -0.07
    _issue
    -0.06
    åIJĪçIJĨåľ°
    -0.06
    odo
    -0.06
    POSITIVE LOGITS
    ä¸ĭåĪĹåħ³äºİ
    0.08
    ä¸ĭåĪĹ
    0.08
    _____
    0.08
    ¶
    0.07
    请éĢīæĭ©
    0.07
     _____
    0.07
    izz
    0.07
    æŁ»
    0.07
    ä¸ĭåĪĹ说æ³ķ
    0.07
    å¿«çľĭ
    0.06
    Activations Density 0.034%

    No Known Activations