© 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. 54943
    Prev
    Next
    INDEX
    Explanations

    parentheses and equations

    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
    å®ľ
    -0.07
    æľį
    -0.07
    NI
    -0.06
    OH
    -0.06
    _ioctl
    -0.06
    é¢ł
    -0.06
    åĪ°æŶ
    -0.06
     Bens
    -0.06
    åIJŀ
    -0.06
    çĽĨèħĶ
    -0.06
    POSITIVE LOGITS
    æĥ¯äºĨ
    0.08
    pend
    0.08
    KeyValue
    0.08
    ÙİØ£
    0.07
     scram
    0.07
    peria
    0.07
    ascript
    0.07
    arse
    0.07
    htable
    0.07
    Listeners
    0.07
    Activations Density 0.014%

    No Known Activations