© 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. 22345
    Prev
    Next
    INDEX
    Explanations

    description of the related art

    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
    ingle
    -0.07
    uo
    -0.06
    ı
    -0.06
    ÄĻ
    -0.06
    '
    -0.06
    esz
    -0.06
    2
    -0.06
    ª
    -0.06
    (
    -0.06
    ãĢĬ
    -0.06
    POSITIVE LOGITS
    /Gate
    0.10
    OperationException
    0.09
    çĹħæĥħåĪĨæŀIJ
    0.09
    æ¡ĪçĶ±
    0.08
    (/^\
    0.08
    åīį款
    0.08
    /Math
    0.08
    PERT
    0.08
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    0.08
    ifax
    0.08
    Activations Density 0.029%

    No Known Activations