© 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. 47576
    Prev
    Next
    INDEX
    Explanations

    book reviews

    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
    èĵĦ
    -0.08
    estes
    -0.08
    æݧåĪ¶çļĦ
    -0.07
    halat
    -0.07
    åĢĶ强
    -0.07
    ajan
    -0.07
    Anywhere
    -0.07
    _docs
    -0.07
    è¦ģæ±Ĥåľ¨
    -0.07
    æݧåĪ¶
    -0.06
    POSITIVE LOGITS
    详尽
    0.10
    客è§Ĥ
    0.10
     detailed
    0.09
    ä¸İåĪĨæŀIJ
    0.09
    åĴĮåĪĨæŀIJ
    0.09
    详
    0.09
    å°±æĺ¯å¯¹
    0.09
    åĪĨæŀIJåĴĮ
    0.09
    criptive
    0.09
    åĪĨæŀIJæĬ¥åijĬ
    0.09
    Activations Density 0.204%

    No Known Activations