© 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. 3810
    Prev
    Next
    INDEX
    Explanations

    Ask a question

    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
    èĻ±
    -0.08
    èĽ¾
    -0.08
    ä¸įèµ·
    -0.07
    失
    -0.07
    精巧
    -0.07
    ç»ĵæŀĦç®Ģåįķ
    -0.07
    ÑĢоди
    -0.07
    éĢĢæį¢
    -0.07
    ÑĥпиÑĤÑĮ
    -0.07
    heim
    -0.07
    POSITIVE LOGITS
    ç»Ī审
    0.07
    å®ĪåĪĻ
    0.07
    ä¸įä»ħè¦ģ
    0.07
     ä»ĬæĹ¥
    0.06
    çļĦè¦ģæ±Ĥ
    0.06
    peon
    0.06
    subcategory
    0.06
    è¦ģæ±Ĥ
    0.06
    ervis
    0.06
    rich
    0.06
    Activations Density 0.002%

    No Known Activations