© 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. 11569
    Prev
    Next
    INDEX
    Explanations

    examples (e.g. .g)

    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
    жÑĮ
    -0.09
    ÑİÑĢи
    -0.09
     Ing
    -0.07
    rive
    -0.07
    æĪĸ以ä¸Ĭ
    -0.07
    пÑĮ
    -0.07
    ¬
    -0.07
    giene
    -0.07
    edur
    -0.07
    á»ij
    -0.07
    POSITIVE LOGITS
    inkle
    0.08
    aki
    0.07
    å¾ĹåĬĽ
    0.07
    æľµ
    0.07
    åıĤè§ģ
    0.06
    cak
    0.06
    endis
    0.06
    êm
    0.06
    ä¸įåı¯æĪĸ缺çļĦ
    0.06
    ARG
    0.06
    Activations Density 0.008%

    No Known Activations