© 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. 51896
    Prev
    Next
    INDEX
    Explanations

    return

    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
    imbus
    -0.08
    ulik
    -0.07
    å¤§åľ£
    -0.07
    ynch
    -0.06
    转æį¢åĻ¨
    -0.06
    utato
    -0.06
    Ư
    -0.06
    å±Ĩ
    -0.06
    åĪĺçķħ
    -0.06
    à§Ĥল
    -0.06
    POSITIVE LOGITS
    orten
    0.09
     return
    0.08
    return
    0.08
    åı¯æĪij
    0.07
    asin
    0.07
    é«ĺ人
    0.07
    ampi
    0.07
    çĥŃæ°Ķ
    0.07
    ikin
    0.07
    _SKIP
    0.07
    Activations Density 0.027%

    No Known Activations