© 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. 39921
    Prev
    Next
    INDEX
    Explanations

    explicitly, all, solving, complete, individually

    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
    _FLUSH
    -0.07
    åĪ©
    -0.07
    æĹłæ³ķæŃ£å¸¸
    -0.06
    undy
    -0.06
    ä¸į容
    -0.06
    iller
    -0.06
    è¿«
    -0.06
    ä¸įåŃĺåľ¨
    -0.06
    Ñģно
    -0.06
    :\/\/
    -0.06
    POSITIVE LOGITS
    æ¯ı次éĥ½
    0.10
    /full
    0.09
    ç¹ģçIJIJ
    0.08
    é«ĺç²¾
    0.08
     full
    0.08
    ç¹ģæĿĤ
    0.08
    éĥ½çŁ¥éģĵ
    0.08
    éĢIJ个
    0.08
    ä¸įå¿ħè¦ģçļĦ
    0.08
    idious
    0.08
    Activations Density 0.077%

    No Known Activations