© 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. 41834
    Prev
    Next
    INDEX
    Explanations

    calculations, formula, score, authorization, synthesis, website, screwed, tours, spinning, filters

    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
    inst
    -0.06
    æĺİ缮
    -0.06
    éĢĤå½ĵçļĦ
    -0.06
    Do
    -0.06
    uny
    -0.06
    çĻ½æĹ¥
    -0.06
    å¹´æŶéĹ´
    -0.06
     Doing
    -0.05
     do
    -0.05
    кеÑĢ
    -0.05
    POSITIVE LOGITS
    ä¸İä¹ĭ
    0.08
    rgan
    0.08
    ä¸ĭåIJĮ
    0.08
    ä¹ĭåĪĹ
    0.08
    =len
    0.08
    _consumer
    0.08
    iferay
    0.07
    ::__
    0.07
     Gret
    0.07
    æĪij们åİ»
    0.07
    Activations Density 0.274%

    No Known Activations