© 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. 1974
    Prev
    Next
    INDEX
    Explanations

    citations journals and authors

    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
    æĬķ
    -0.07
    åħ±åIJĮè¿ĽæŃ¥
    -0.07
    sock
    -0.06
    èĢ½
    -0.06
    -progress
    -0.06
    æ´ĭæ´ĭ
    -0.06
    çĨŁ
    -0.06
    以
    -0.06
    éķ¿çŁŃ
    -0.06
    è°ģ家
    -0.06
    POSITIVE LOGITS
    æ¯ı天æľī
    0.08
    éb
    0.07
     ê¹ĬìĿĢ
    0.07
    isser
    0.07
    Ïģαι
    0.07
    æ¸ħ宫
    0.07
    δά
    0.07
    éļıæŶ
    0.07
    iversal
    0.07
    artz
    0.07
    Activations Density 0.014%

    No Known Activations