© 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. 31919
    Prev
    Next
    INDEX
    Explanations

    addressing yourself or others

    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
    <|box_end|>
    -0.09
    ].'
    -0.07
    chè
    -0.07
    oret
    -0.07
    Ùĭ
    -0.07
    çĦ¶å¤§
    -0.07
    大ä¼ļä¸Ĭ
    -0.07
    èĬĤå¿«ä¹IJ
    -0.07
    ANNOT
    -0.07
    ÙĮÙij
    -0.07
    POSITIVE LOGITS
    —they
    0.08
    å°±çŁ¥éģĵ
    0.08
    å°±çŁ¥éģĵäºĨ
    0.08
    ä½łå°±ä¼ļ
    0.08
    å°±ä¼ļåıijçİ°
    0.07
    并ç»ĵåIJĪ
    0.07
     attent
    0.07
     carefully
    0.07
    æĽ´ä¸įè¦ģ
    0.07
    è®¤çľŁéĺħ读
    0.07
    Activations Density 0.005%

    No Known Activations