© 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. 24472
    Prev
    Next
    INDEX
    Explanations

    solve for a variable

    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
    endencies
    -0.07
    å¢
    -0.07
    大åĬŁ
    -0.07
    agara
    -0.07
    åIJĮæĹ¶è¿Ľè¡Į
    -0.07
    creating
    -0.07
    è¡£è£Ļ
    -0.07
    ÙĦÙĬÙĩ
    -0.07
    ucie
    -0.07
    нÑĮ
    -0.06
    POSITIVE LOGITS
    kit
    0.08
    æ±Ĥå¾Ĺ
    0.07
    Kit
    0.07
    luss
    0.07
    åı¯å¾Ĺ
    0.07
    ç¡®
    0.06
    å·¥ç¨ĭç³»
    0.06
    irs
    0.06
    ä½łå°±èĥ½
    0.06
    Emer
    0.06
    Activations Density 0.004%

    No Known Activations