© 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. 15589
    Prev
    Next
    INDEX
    Explanations

    is an

    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
    зов
    -0.08
    设å®ļçļĦ
    -0.07
    æīĵçĿĢ
    -0.07
    åĩºå¥ĩ
    -0.06
    åı¯æĺ¯åľ¨
    -0.06
    вов
    -0.06
    éĿ¢å¹¿
    -0.06
    _variant
    -0.06
    chin
    -0.06
    arder
    -0.06
    POSITIVE LOGITS
    —the
    0.10
    åºĶæĺ¯
    0.09
    ä½ľä¸º
    0.08
    æĺ¯è¯¥
    0.08
    èģ·
    0.08
    (the
    0.08
     berupa
    0.08
    åħ¶å®ŀå°±æĺ¯
    0.07
    åį³æĺ¯
    0.07
    缸å½ĵäºİ
    0.07
    Activations Density 0.275%

    No Known Activations