© 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. 60382
    Prev
    Next
    INDEX
    Explanations

    reducing environmental impact

    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
    ount
    -0.08
    oshi
    -0.08
    æŶéĢŁ
    -0.08
    å°±æĢķ
    -0.08
    çĻ»å½ķåIJİ
    -0.07
    çļ®ä¹¦
    -0.07
    æĩĴæķ£
    -0.07
    —even
    -0.07
    _accepted
    -0.07
    _attachments
    -0.07
    POSITIVE LOGITS
    æĭ¯
    0.08
    åīįèĢħ
    0.07
    èİ
    0.07
    æĹ¢è¦ģ
    0.07
    nÄĽ
    0.06
    診
    0.06
    æĹ¢æĺ¯
    0.06
    cé
    0.06
    SIGN
    0.06
    缼
    0.06
    Activations Density 0.013%

    No Known Activations