© 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. 60000
    Prev
    Next
    INDEX
    Explanations

    methyl groups, hydrocarbon chains

    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
    Negative Logits
    meld
    -0.08
    çĬĢåĪ©
    -0.08
    laut
    -0.07
     Forced
    -0.07
    ?(:
    -0.07
    æĿ¡æĿ¡
    -0.07
    ä¹ĭçªĹ
    -0.07
    æµ·çĩķ
    -0.07
    æ¸Ĭåįļ
    -0.07
    roit
    -0.07
    POSITIVE LOGITS
    ä¸ĺ
    0.07
    èĮĤ
    0.07
     fatty
    0.07
     shielding
    0.06
    Shield
    0.06
    exels
    0.06
     unaffected
    0.06
     ада
    0.06
     shield
    0.06
    平庸
    0.06
    Activations Density 0.020%

    No Known Activations