© 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. 64576
    Prev
    Next
    INDEX
    Explanations

    prob of sequences

    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
    丽åįİ
    -0.07
    ott
    -0.07
    æĺ¯å½ĵåīį
    -0.07
    zeb
    -0.07
    eck
    -0.07
    elh
    -0.06
    çŁ¥éģĵåIJĹ
    -0.06
    ÑĩÑĭ
    -0.06
    çļĦåı¦ä¸Ģ
    -0.06
    ãģŁãģ¾
    -0.06
    POSITIVE LOGITS
    ivan
    0.08
    isle
    0.08
    alie
    0.08
    åºĥåijĬãģ¯
    0.08
    TypeDef
    0.08
    ä»ĸè¿ĺæĺ¯
    0.07
    åĿļå®ļä¿¡å¿ĥ
    0.07
    á»ĭu
    0.07
    åŃ¦ä»¥èĩ´çĶ¨
    0.07
    ëĬĶëį°
    0.07
    Activations Density 0.007%

    No Known Activations