© 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. 24368
    Prev
    Next
    INDEX
    Explanations

    evidence and proof

    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
    åIJij导
    -0.08
    å¼ķé¢Ĩ
    -0.07
    çĶ±é«ĺ
    -0.07
    åıĹåĪ¶
    -0.07
    ç»ı缸åħ³éĥ¨éŨæī¹åĩĨ
    -0.07
    chine
    -0.07
    è¿ĩä¸Ģ次
    -0.07
    olen
    -0.07
    解åĨ³çļĦéĹ®é¢ĺ
    -0.07
    æ¸ĭ
    -0.07
    POSITIVE LOGITS
    è¯ģæį®
    0.11
     evidence
    0.11
    çŃīè¯ģæį®
    0.11
    åıĸè¯ģ
    0.11
    Evidence
    0.10
    举è¯ģ
    0.10
     Evidence
    0.10
    è¯ģæĺİ
    0.09
    è¯ģæĺİäºĨ
    0.09
    หลัà¸ģà¸IJาà¸Ļ
    0.09
    Activations Density 0.013%

    No Known Activations