© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7212
    Prev
    Next
    INDEX
    Explanations

    confession and questioning

    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
    æıIJæ¡Ī
    -0.07
     Dumpster
    -0.07
     phot
    -0.06
    èĴ¸
    -0.06
    èĪĪ
    -0.06
    èµĦæºIJçļĦ
    -0.06
    gaz
    -0.06
    庶
    -0.06
    ç«łç¨ĭå¤ĩæ¡Ī
    -0.06
    èŀŁ
    -0.06
    POSITIVE LOGITS
    ç¬Ķå½ķ
    0.11
    ä¾Ľè¿°
    0.10
    åĽŀçŃĶéĹ®é¢ĺ
    0.10
    认罪
    0.10
    èĩªé¦ĸ
    0.10
    å½ķéŁ³
    0.10
     confession
    0.09
    å¦Ĥå®ŀä¾Ľè¿°
    0.09
     interrog
    0.09
    ä¿¡çļĦ
    0.09
    Activations Density 0.046%

    No Known Activations