© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    dates or quantities

    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
    olina
    -0.07
    驹
    -0.07
    éļĶ
    -0.06
    atera
    -0.06
    QUI
    -0.06
    AMP
    -0.06
    vs
    -0.06
    ons
    -0.06
    ä¸ĭéĿ¢æĺ¯
    -0.06
    GI
    -0.06
    POSITIVE LOGITS
    OrNil
    0.08
    åIJĥä¸į
    0.07
    htub
    0.07
    igm
    0.07
    RenderingContext
    0.06
    anies
    0.06
    ساÙĨ
    0.06
    èĥ±
    0.06
    plode
    0.06
    imest
    0.06
    Activations Density 0.036%

    No Known Activations