© 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. 14445
    Prev
    Next
    INDEX
    Explanations

    direction

    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
    çĻ½æĹ¥
    -0.08
    éļı身æIJºå¸¦
    -0.07
    çķĻåľ¨äºĨ
    -0.07
     nationwide
    -0.07
    å¤ļæĸ¹éĿ¢
    -0.07
    åľ¨åºĬä¸Ĭ
    -0.07
    amor
    -0.07
    ulu
    -0.07
    å¦ĤåĪĿ
    -0.07
     Provinc
    -0.07
    POSITIVE LOGITS
    主èIJ¥
    0.09
    ä¸įè¿ľ
    0.09
    ä¸įè¿ľå¤Ħ
    0.08
    è¿ijå¹³
    0.08
     dãy
    0.08
    左侧
    0.07
    ôn
    0.07
    æĸ°å¼Ģ
    0.07
    ç´§éĤ»
    0.07
    侧
    0.07
    Activations Density 0.191%

    No Known Activations