© 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. 46003
    Prev
    Next
    INDEX
    Explanations

    then

    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
    çļĦéĤ£ç§į
    -0.08
    æīĢ以她
    -0.08
    èĻ½çĦ¶æĪij们
    -0.08
    byname
    -0.08
    æīĢ以ä»ĸ们
    -0.07
    èĻ½çĦ¶çİ°åľ¨
    -0.07
    comings
    -0.07
    plevel
    -0.07
    çĤ¹è¿ĻéĩĮ
    -0.07
    ELO
    -0.07
    POSITIVE LOGITS
    éĹ®é¢ĺæĿ¥äºĨ
    0.11
    å²Ĥä¸įæĺ¯
    0.07
    ucc
    0.07
    çĦ¶å¤§
    0.07
    fore
    0.07
    为ä½ķ
    0.07
     onda
    0.07
    \Log
    0.06
    ëĭ¤ë©´
    0.06
     ÑĥÑĩаÑģÑĤÑĮ
    0.06
    Activations Density 0.026%

    No Known Activations