© 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. 44417
    Prev
    Next
    INDEX
    Explanations

    homography

    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
     RequestMethod
    -0.08
    ÐľÐķÐĿ
    -0.08
    _oid
    -0.08
     iepazÄ«Å¡anÄģs
    -0.08
    ׳×Ļ×Ķ
    -0.08
    flen
    -0.08
    /Set
    -0.08
    sak
    -0.08
    交åĪ°
    -0.08
    _DSP
    -0.08
    POSITIVE LOGITS
    unk
    0.07
    A
    0.06
    lete
    0.06
    ungan
    0.06
     ↵
    0.06
    ç»Ŀ
    0.06
    ch
    0.06
    uh
    0.06
    çĪ¶
    0.06
    ella
    0.06
    Activations Density 0.701%

    No Known Activations