© 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. 32081
    Prev
    Next
    INDEX
    Explanations

    you know

    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
    æīĢå±ŀåĪĨç±»
    -0.09
    缸åħ³éĹ®çŃĶ
    -0.08
    urier
    -0.08
    æĪijæĽ´
    -0.07
    nehmer
    -0.07
    ÙĪدÙĩ
    -0.07
    Bahn
    -0.07
    à¹Ģหà¸Ļืà¸Ń
    -0.07
    æĪijåıªå¥½
    -0.07
    _ISO
    -0.07
    POSITIVE LOGITS
    让çĶŁæ´»
    0.07
    á´Ħ
    0.06
    éŁ
    0.06
     /^[
    0.06
     wording
    0.06
     canh
    0.06
    æĢ»æ¯Ķ
    0.06
    bbbb
    0.06
    ä¸Ģåħ±
    0.06
    èģĶè°Ĭ
    0.06
    Activations Density 0.001%

    No Known Activations