© 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. 16656
    Prev
    Next
    INDEX
    Explanations

    ORDER, PDF, unsafe, require

    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
    arl
    -0.09
    iveness
    -0.08
    otec
    -0.08
    IBUT
    -0.08
    ailable
    -0.08
    æ±Ĥ人
    -0.07
    undur
    -0.07
    jut
    -0.07
    汹汹
    -0.07
    kees
    -0.07
    POSITIVE LOGITS
    zes
    0.07
    åľ¨åĨĮ
    0.06
    çļĦä¸Ģæł·
    0.06
    ï¸ı
    0.06
    zilla
    0.06
    razier
    0.06
    ãģª
    0.06
    饶
    0.06
    éĺģ
    0.06
    "."
    0.06
    Activations Density 0.001%

    No Known Activations