© 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. 32208
    Prev
    Next
    INDEX
    Explanations

    surface property descriptions

    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
    ìĿ´íĦ°
    -0.07
    çĻ¾å·Ŀ
    -0.07
    afia
    -0.07
    cala
    -0.06
    å¾®åķĨ
    -0.06
    åĴĮéľĢæ±Ĥ
    -0.06
    èĺĭ
    -0.06
    éľĢè¦ģåIJĮ
    -0.06
    æĢ§æ¬²
    -0.06
    ombs
    -0.06
    POSITIVE LOGITS
    为äºĨæıIJé«ĺ
    0.08
    æ¯ıå¹³æĸ¹ç±³
    0.07
    æĸ½å·¥è´¨éĩı
    0.07
     oriented
    0.07
    éķ¿æľŁä»İäºĭ
    0.07
    表éĿ¢
    0.07
     Recent
    0.07
     Presence
    0.06
    éĶ¦èµĽ
    0.06
    æĸ½å·¥å·¥èīº
    0.06
    Activations Density 0.061%

    No Known Activations