© 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. 37752
    Prev
    Next
    INDEX
    Explanations

    bug reports

    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
    ä¸įå¼Ģ
    -0.07
    ãĥķãĤ©ãĥ³
    -0.07
    koch
    -0.07
    ebab
    -0.07
    endela
    -0.07
    æĸijåĿĹ
    -0.07
    èħ¹åľ°
    -0.07
    æı£
    -0.07
    oy
    -0.07
    annage
    -0.07
    POSITIVE LOGITS
    ç¦ıåħĭæĸ¯
    0.08
    æŃ¥éª¤
    0.08
    使å®ĥ
    0.08
    å®ĮæĪIJåIJİ
    0.07
     Charges
    0.07
    åħĪåľ¨
    0.07
    çĶµæŀģ
    0.07
     Higgins
    0.07
     oxidation
    0.07
     charges
    0.07
    Activations Density 0.001%

    No Known Activations