© 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. 49199
    Prev
    Next
    INDEX
    Explanations

    Configure paths

    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
    æĪĴ
    -0.08
    çĺ¾
    -0.08
    鲫
    -0.08
    çĵ¶é¢Ī
    -0.07
     Nga
    -0.07
    bang
    -0.07
    cobra
    -0.07
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    olino
    -0.07
    涨
    -0.07
    POSITIVE LOGITS
    æĿ¥åĪ¤æĸŃ
    0.08
     Ñģмо
    0.07
     recipro
    0.07
    æĢĢ
    0.07
     fellow
    0.07
    è¯ĦåĪ¤
    0.07
    omens
    0.07
    èĩªåı¤
    0.06
     Wol
    0.06
    iefs
    0.06
    Activations Density 0.003%

    No Known Activations