© 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. 27498
    Prev
    Next
    INDEX
    Explanations

    以ä¸Ĭ以èżé…³ çľ´ç®¡

    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
    请ä¸İæĪij们èģĶç³»
    -0.09
    .fil
    -0.09
    á»ĩu
    -0.08
    LOSE
    -0.08
    没æŶéĹ´
    -0.08
    çĤ¹åĩ»æŁ¥çľĭçŃĶæ¡Ī
    -0.08
    ERSIST
    -0.08
    ĩ´
    -0.08
    åįİ西
    -0.08
    SPATH
    -0.08
    POSITIVE LOGITS
    以ä¸Ĭæĺ¯
    0.08
    以ä¸Ĭå°±æĺ¯
    0.06
    以ä¸Ĭ
    0.06
    úr
    0.06
    ike
    0.06
    大çİĭ
    0.06
    以ä¸ĬçļĦ
    0.06
    以ä¸ĬåĨħ容
    0.06
    æĢ»ç»ĵ
    0.06
    åį³æĺ¯
    0.06
    Activations Density 0.002%

    No Known Activations