© 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. 14851
    Prev
    Next
    INDEX
    Explanations

    min read

    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
    åħ·æľī以ä¸ĭ
    -0.09
    表
    -0.07
    uria
    -0.06
    usi
    -0.06
    æľī以ä¸ĭ
    -0.06
    以ä¸ĭåĩł
    -0.06
    以ä¸ĭæĺ¯
    -0.06
    追
    -0.06
    (...)
    -0.06
    Unc
    -0.05
    POSITIVE LOGITS
    ë¥
    0.09
    ém
    0.09
    ajem
    0.08
    пеÑĢа
    0.08
    Ø´ÙĨ
    0.08
    å±ħåīį
    0.08
    loat
    0.08
    à¸ķั
    0.08
    ä¸įç»ı
    0.08
    ç®Ģç®Ģåįķ
    0.08
    Activations Density 0.078%

    No Known Activations