© 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. 51928
    Prev
    Next
    INDEX
    Explanations

    historical periods or names

    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
    æĬķ稿éĤ®ç®±
    -0.08
    altern
    -0.08
    嫦
    -0.07
     ÑģамоÑĩ
    -0.07
    orgia
    -0.07
     usual
    -0.07
    china
    -0.07
    横è¡Į
    -0.07
    åij¨åĽ´çݯå¢ĥ
    -0.07
     استط
    -0.07
    POSITIVE LOGITS
    å½ĵå¹´çļĦ
    0.15
    å½ĵå¹´
    0.15
    çķ¶å¹´
    0.13
    å½ĵåĪĿ
    0.12
    -era
    0.12
    legacy
    0.12
    éģĹçķĻ
    0.12
     legacy
    0.11
    æĹ¶ä»£çļĦ
    0.11
    æŧåĿĢ
    0.11
    Activations Density 0.807%

    No Known Activations