© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23050
    Prev
    Next
    INDEX
    Explanations

    code parsing with numbers and tags

    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
    宦
    -0.07
     tap
    -0.06
    tap
    -0.06
    è¿Ļ个åIJįåŃĹ
    -0.06
    atap
    -0.06
     all
    -0.06
    åĶ®æ¥¼å¤Ħ
    -0.06
     name
    -0.05
    andon
    -0.05
    轩
    -0.05
    POSITIVE LOGITS
    anty
    0.09
    åįģä¹Ŀå±Ĭ
    0.08
     обо
    0.08
    áĥĿáĥĵ
    0.08
    ýt
    0.08
    ectoria
    0.07
    _attached
    0.07
    errat
    0.07
    ׳×Ļ×Ķ
    0.07
    eldom
    0.07
    Activations Density 0.007%

    No Known Activations