© 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. 29084
    Prev
    Next
    INDEX
    Explanations

    alternatives and replacements

    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
    aros
    -0.08
    赡
    -0.07
     bá»ĵi
    -0.07
    ÙĪار
    -0.07
    æĺ¯éĿł
    -0.07
    设计åĪ¶ä½ľ
    -0.07
    uem
    -0.07
    æĸ¹åIJijçļĦ
    -0.06
     pilote
    -0.06
    ¡
    -0.06
    POSITIVE LOGITS
    å®īåħ¨åı¯éĿł
    0.07
    æ¾İæ¹ĥ
    0.07
    æĽ¿ä»£åĵģ
    0.07
     Altern
    0.07
    ispens
    0.07
     replacement
    0.07
    éĢŁåº¦å¿«
    0.07
    Replacement
    0.07
    æĽ¿ä»£
    0.07
     quickly
    0.07
    Activations Density 0.293%

    No Known Activations