© 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. 27866
    Prev
    Next
    INDEX
    Explanations

    ordered lists or parenthesized items

    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
    以ä¸ĬçļĦ
    -0.09
    engin
    -0.07
    åľ¨åIJij
    -0.07
    andon
    -0.07
    noinspection
    -0.07
    ä¸Ĭè¿°
    -0.06
    estream
    -0.06
    ä¿¡æģ¯å¹³åı°
    -0.06
    ersh
    -0.06
    iare
    -0.06
    POSITIVE LOGITS
    çĦ¶å¤§
    0.08
    ä¹İåħ¶
    0.08
    ä¹İ
    0.08
    åıĸåĨ³
    0.08
    æĬĬä»ĸ们
    0.07
    ä¸įèIJ½
    0.07
    éªı
    0.07
    çŁ¥éģĵä»ĸ
    0.07
    usen
    0.07
    çĦ¶
    0.07
    Activations Density 0.001%

    No Known Activations