© 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. 61012
    Prev
    Next
    INDEX
    Explanations

    so as to

    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
    æĹ¥åĪ¶
    -0.07
    èµĭ
    -0.07
    çĶ¨æĿ¥
    -0.07
    åĪ«çļĦ
    -0.07
    Undefined
    -0.07
    è®°èĢħä»İ
    -0.06
    æĸ°å¼Ģ
    -0.06
     ìĥĪë¡Ńê²Į
    -0.06
    解åĨ³åĬŀæ³ķ
    -0.06
    enger
    -0.06
    POSITIVE LOGITS
    å°½åı¯èĥ½çļĦ
    0.09
    å°½éĩı
    0.09
    åıªæĺ¾ç¤º
    0.09
    å°½éĩıå°ij
    0.08
    å°½éĩıåĩıå°ij
    0.08
    å°½åı¯èĥ½
    0.08
    åıª
    0.08
     макÑģималÑĮно
    0.08
    antz
    0.08
    å°½éĩıéģ¿åħį
    0.08
    Activations Density 0.135%

    No Known Activations