© 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. 7569
    Prev
    Next
    INDEX
    Explanations

    curve fitting and representations

    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
    er
    -0.09
    s
    -0.08
    entifier
    -0.08
     hụt
    -0.08
    à¸Ĺà¹Į
    -0.08
    mals
    -0.07
    ر
    -0.07
    sce
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    /her
    -0.07
    POSITIVE LOGITS
    Ø©
    0.10
    aceous
    0.09
    ancell
    0.08
    inality
    0.08
    usel
    0.08
    ÑĨом
    0.08
    ancellable
    0.08
    ÑĩаÑĤ
    0.08
    ighed
    0.08
    ToObject
    0.08
    Activations Density 0.017%

    No Known Activations