© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17645
    Prev
    Next
    INDEX
    Explanations

    rule-making

    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
    èĻĶè¯ļ
    -0.08
     sincer
    -0.07
    pg
    -0.07
    reas
    -0.07
    gång
    -0.07
    rát
    -0.07
    gantian
    -0.07
    ä»»çĶ±
    -0.07
    èĦijè¡Ģ管
    -0.07
    èģª
    -0.06
    POSITIVE LOGITS
    è¡ĮæĶ¿å¤įè®®
    0.09
    è¿Ŀæ³ķ
    0.09
    è¡ĮæĶ¿è¡Į为
    0.08
    ä½ľåĩºçļĦ
    0.08
    è¡ĮæĶ¿æľºåħ³
    0.08
    ä¾Ŀæ³ķè¡ĮæĶ¿
    0.08
    æī§æ³ķ
    0.08
    å¤įè®®
    0.08
    便æ°ij
    0.08
    åIJ¬è¯ģ
    0.08
    Activations Density 0.008%

    No Known Activations