© 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. 37712
    Prev
    Next
    INDEX
    Explanations

    table separators

    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
    好ä¸į
    -0.08
    quired
    -0.08
    ulary
    -0.08
    ново
    -0.08
    els
    -0.07
    ToDevice
    -0.07
    icable
    -0.07
    oron
    -0.07
    为æķ°
    -0.07
    avail
    -0.07
    POSITIVE LOGITS
    worthy
    0.07
    omp
    0.06
    ÙģØ´
    0.06
    ær
    0.06
    æĭħ
    0.06
    enes
    0.06
     eksk
    0.06
    rea
    0.06
    æĬ¼
    0.06
    CTX
    0.06
    Activations Density 0.004%

    No Known Activations