© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15199
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
    ghan
    -0.06
    -engine
    -0.06
     Halb
    -0.06
    sat
    -0.06
    åĥļ
    -0.06
    ×ķ×ĸ
    -0.06
    ä¸įåºĶæ±Ĥ
    -0.06
    éĽªä¸Ń
    -0.06
     presentations
    -0.06
    TERN
    -0.06
    POSITIVE LOGITS
    çŃ¾ç½²
    0.10
    çŃ¾è®¢
    0.10
    æī¿è¯ºä¹¦
    0.10
    æĿ¡æ¬¾
    0.09
    é¡»çŁ¥
    0.09
     risks
    0.09
    åijĬçŁ¥ä¹¦
    0.09
     пÑĢедÑĥпÑĢе
    0.09
    é£İéĻ©åĴĮ
    0.08
    çŃ¾è®¢çļĦ
    0.08
    Activations Density 0.440%

    No Known Activations