© 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. 38403
    Prev
    Next
    INDEX
    Explanations

    exercise or invoke

    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
    áĥ£áĥł
    -0.09
    áĥ£áĥłáĥĺ
    -0.09
    à¥įà¤Ł
    -0.08
    engel
    -0.08
    ixon
    -0.08
    翼翼
    -0.08
    ting
    -0.08
    orr
    -0.08
    ÅĻÃŃzenÃŃ
    -0.08
    verting
    -0.08
    POSITIVE LOGITS
    able
    0.08
    ables
    0.08
    èĢħåľ¨
    0.07
    æŃ£å½ĵ
    0.07
    å®Įæ¯ķ
    0.07
    好èĩªå·±çļĦ
    0.07
    onaut
    0.07
    åħ¶èģĮ
    0.07
    ande
    0.07
    äºĨä¸Ģ次
    0.06
    Activations Density 0.009%

    No Known Activations