© 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. 25022
    Prev
    Next
    INDEX
    Explanations

    except for

    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
    δÎŃ
    -0.08
    åµĺ
    -0.07
     sent
    -0.07
    æ¡
    -0.07
    _Send
    -0.06
     Arithmetic
    -0.06
     pub
    -0.06
    æĽ´éļ¾
    -0.06
     Hotline
    -0.06
    asename
    -0.06
    POSITIVE LOGITS
    æĪĸéĢļè¿ĩ
    0.11
    ìĿ´ê±°ëĤĺ
    0.10
     либо
    0.09
    åĢŁåĬ©
    0.09
    éĶĻ误æĪĸ
    0.09
    æĪĸåĪ©çĶ¨
    0.09
     exceptions
    0.09
     circum
    0.09
    çī¹æ®ĬæĥħåĨµ
    0.08
    ä¾ĭå¤ĸ
    0.08
    Activations Density 0.188%

    No Known Activations