© 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. 11269
    Prev
    Next
    INDEX
    Explanations

    equals sign or EQUAL

    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
    _sensitive
    -0.07
    çĻ»ä¸ĬäºĨ
    -0.07
    rone
    -0.07
    <|box_end|>
    -0.06
    æİĴè¡Į
    -0.06
     cycles
    -0.06
    oyo
    -0.06
    ä½ıäºĨ
    -0.06
     cycle
    -0.06
     conserv
    -0.06
    POSITIVE LOGITS
    newline
    0.08
    ardin
    0.08
    ulet
    0.07
    TextStyle
    0.07
    é½IJ
    0.07
    غت
    0.07
    é½IJé½IJ
    0.07
    涯
    0.07
    åıĬè¦ģæ±Ĥ
    0.07
    ç´§æİ¥çĿĢ
    0.06
    Activations Density 0.036%

    No Known Activations