© 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. 11173
    Prev
    Next
    INDEX
    Explanations

    multiple choice options

    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
    orious
    -0.07
    -
    -0.07
    ikus
    -0.06
     ((!
    -0.06
    åŁºæľ¬
    -0.06
    éri
    -0.06
    kamp
    -0.06
    olor
    -0.06
    ãĥªãĤ¢
    -0.06
    丰å¯ĮçļĦ
    -0.06
    POSITIVE LOGITS
    ×ij×ķת
    0.08
    panies
    0.08
    ires
    0.08
    älter
    0.08
    ESCO
    0.08
    /car
    0.07
    tera
    0.07
    cest
    0.07
     ìĨĮìļĶ
    0.07
    èĪª
    0.07
    Activations Density 0.008%

    No Known Activations