© 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. 22494
    Prev
    Next
    INDEX
    Explanations

    operating business/assets or, subsidiary

    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
    akai
    -0.08
     Penyel
    -0.08
    åĥı
    -0.08
     whatever
    -0.08
    ä»Ĭ天çļĦ
    -0.08
    伸åĩºæīĭ
    -0.07
    rete
    -0.07
    è¿ĻæŶçļĦ
    -0.07
    adou
    -0.07
    æŁIJ个
    -0.07
    POSITIVE LOGITS
    åħ¬åħģ
    0.08
    审æħİ
    0.08
    æļĤæľª
    0.08
    åıĹ让
    0.08
    ä¸İ被åijĬ
    0.08
    涤
    0.08
    å°Ĩ该
    0.08
    åħ¶ä¸İ
    0.08
    ä»ħ为
    0.07
    åĿĩå·²
    0.07
    Activations Density 0.003%

    No Known Activations