© 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. 25058
    Prev
    Next
    INDEX
    Explanations

    copyright and 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
    ious
    -0.10
    fus
    -0.08
    usak
    -0.08
    iously
    -0.08
    à¹Ģสริ
    -0.08
    aliza
    -0.08
    óta
    -0.07
    cai
    -0.07
    ialized
    -0.07
    еÑĨ
    -0.07
    POSITIVE LOGITS
    endu
    0.07
    ãĤ¹ãĥĿãĥĥãĥĪ
    0.07
    chter
    0.07
    agoon
    0.07
    idor
    0.06
    å¸ļ
    0.06
    ivant
    0.06
    绣
    0.06
    0.06
    encing
    0.06
    Activations Density 0.044%

    No Known Activations