© 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. 10910
    Prev
    Next
    INDEX
    Explanations

    constraint, cone programs, binary analysis

    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
    çĶ°éĩİ
    -0.07
    aac
    -0.07
    αιο
    -0.07
     NAMES
    -0.07
     ném
    -0.06
    æ¯
    -0.06
    rut
    -0.06
    伦
    -0.06
    .Green
    -0.06
    ĸ
    -0.06
    POSITIVE LOGITS
     Karn
    0.08
     Constraint
    0.08
    bern
    0.07
    å¼ķåħ¥
    0.07
    -binary
    0.07
     constraint
    0.07
     relaxation
    0.07
     rÃłng
    0.07
    aggi
    0.07
    ãĤµãĤ¤
    0.07
    Activations Density 0.033%

    No Known Activations