© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 4350
    Prev
    Next
    INDEX
    Explanations

    License sections

    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
    </think>
    -0.08
    avenport
    -0.07
    ieger
    -0.06
    nev
    -0.06
    æĪ·æĻĵ
    -0.06
    ç¬Ķ趣éĺģ
    -0.06
     intervening
    -0.06
    ụy
    -0.06
    uerdo
    -0.06
    åĽ¢
    -0.06
    POSITIVE LOGITS
    å¼Ģç®±
    0.08
     `.
    0.08
     Github
    0.08
    æĶ¯æĮģä¸İ
    0.08
    鸣
    0.08
    å±Ĭæ¯ķä¸ļçĶŁ
    0.08
     feel
    0.08
     `$
    0.08
    tap
    0.08
    _NOTE
    0.07
    Activations Density 0.448%

    No Known Activations