© 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. 34893
    Prev
    Next
    INDEX
    Explanations

    searching methods and code

    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
    ä¸įå¿ħ
    -0.09
    没å¿ħè¦ģ
    -0.08
    ä¸įå¿ħè¦ģ
    -0.07
    ä¸įéľĢ
    -0.07
    ä¸įä¸Ģ
    -0.07
    inous
    -0.07
    iar
    -0.07
    lade
    -0.07
    ä»ħéľĢ
    -0.07
    -ahead
    -0.07
    POSITIVE LOGITS
     ninguno
    0.12
    æī¾ä¸įåĪ°
    0.12
     ninguna
    0.11
    没æľīä¸Ģ个
    0.11
    éĥ½æ²¡æľī
    0.11
    çļĦä»»ä½ķ
    0.10
    ä»»ä½ķä¸Ģç§į
    0.10
    éĥ½æĹłæ³ķ
    0.10
    没æľīæī¾åĪ°
    0.10
    ä¸Ń没æľī
    0.10
    Activations Density 0.361%

    No Known Activations