© 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. 1236
    Prev
    Next
    INDEX
    Explanations

    struct before like

    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
     DefaultValue
    -0.07
    å·®äºĨ
    -0.06
     rem
    -0.06
    IPC
    -0.06
     liv
    -0.06
    selectedIndex
    -0.06
    å·®ä¸į
    -0.06
    æĬ¥åijĬä¸Ń
    -0.06
    ona
    -0.06
    åĥµ
    -0.06
    POSITIVE LOGITS
    æĪijåĮº
    0.08
    áp
    0.08
    leck
    0.08
    åħ¸åŀĭçļĦ
    0.07
    oriously
    0.07
    uas
    0.07
    çĶ¨åĵģæľīéĻIJåħ¬åı¸
    0.07
    Sdk
    0.07
    èĭ±æĸĩåIJįåŃĹ
    0.07
    atz
    0.07
    Activations Density 0.140%

    No Known Activations