© 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. 1981
    Prev
    Next
    INDEX
    Explanations

    variety of topics

    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
    å²ģå²ģ
    -0.08
    åIJįåī¯åħ¶å®ŀçļĦ
    -0.08
    çİĸ
    -0.07
    ä¼łç»Ļ
    -0.07
    è¿ľæµģ
    -0.07
    lsi
    -0.07
    åħ¶ä¹IJ
    -0.07
    ARGE
    -0.07
    ادÙĬ
    -0.07
    empos
    -0.07
    POSITIVE LOGITS
    æĬĬäºĭæĥħ
    0.09
    åľ¨è¡ĮåĬ¨
    0.09
    äºĭçī©
    0.08
    åĽłæŀľ
    0.08
    äºĭçī©çļĦ
    0.08
    çľ¼åīįçļĦ
    0.08
    解åĨ³éĹ®é¢ĺçļĦ
    0.08
    æĪĸå¤ļ
    0.07
    aka
    0.07
    å·²çŁ¥
    0.07
    Activations Density 0.106%

    No Known Activations