© 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. 27273
    Prev
    Next
    INDEX
    Explanations

    suppose

    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
    lew
    -0.08
    éĥ¨å°±
    -0.07
    aben
    -0.07
    ffc
    -0.07
    åĿĤ
    -0.07
    æĢİä¹Īä¹Ł
    -0.07
     favourable
    -0.07
    cy
    -0.07
    acz
    -0.06
     fucks
    -0.06
    POSITIVE LOGITS
    enes
    0.07
    ä¾
    0.07
    enia
    0.07
    enberg
    0.07
     Blanch
    0.07
    åѦæ³ķ
    0.06
    ×ł×¡
    0.06
    èĬ±ä¸Ģ
    0.06
    çİĭä¹ĭ
    0.06
    uest
    0.06
    Activations Density 0.023%

    No Known Activations