© 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. 65062
    Prev
    Next
    INDEX
    Explanations

    modulation

    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
    wards
    -0.08
    аем
    -0.08
    ognito
    -0.07
    мбÑĥ
    -0.07
    WARDS
    -0.07
    falls
    -0.07
    åįļçī©éĻ¢
    -0.07
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļà¹Į
    -0.07
     Pública
    -0.07
    egner
    -0.07
    POSITIVE LOGITS
    ding
    0.10
    Ùij
    0.09
    ierung
    0.08
    ugno
    0.08
    yssey
    0.08
    .exports
    0.08
    aily
    0.08
    ectomy
    0.08
    amente
    0.08
    ality
    0.07
    Activations Density 0.037%

    No Known Activations