© 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. 58992
    Prev
    Next
    INDEX
    Explanations

    depends on, resist chemical, redeem it

    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
     Mato
    -0.07
    egal
    -0.06
    ubin
    -0.06
    nc
    -0.06
    èį¸
    -0.06
    ingle
    -0.06
    Ù°
    -0.06
    强
    -0.06
    quel
    -0.06
    è½¬æľº
    -0.06
    POSITIVE LOGITS
    åıĪå¦Ĥ
    0.10
    pah
    0.09
    åĴĮç¾İåĽ½
    0.08
    ¶
    0.08
    è¡£èįī
    0.07
    åı¤å±ĭ
    0.07
    ault
    0.07
    IJ
    0.07
    RATION
    0.07
    AGO
    0.07
    Activations Density 0.178%

    No Known Activations