© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 852
    Prev
    Next
    INDEX
    Explanations

    . punctuation

    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
    izon
    -0.07
    ãģĿ
    -0.07
    éĻĩ
    -0.07
    ãģijãģ©ãģŃ
    -0.07
    ä¸įæĦ§æĺ¯
    -0.07
    ä¸įæĦ§
    -0.07
     Planta
    -0.07
    plemented
    -0.07
    建议大家
    -0.07
    urma
    -0.07
    POSITIVE LOGITS
    æľĢæĢķ
    0.09
    主è¦ģåĪĨ为
    0.08
     traditionally
    0.08
    éĢļ常éľĢè¦ģ
    0.08
    åħ¶ä¸ŃæľĢ
    0.08
    èĢĮä»Ĭ
    0.07
    aci
    0.07
    åħ¶ä¸Ńä¸Ģ个
    0.07
    éĥ½å¸ĮæľĽ
    0.07
    æľĢç®Ģåįķ
    0.06
    Activations Density 0.296%

    No Known Activations