© 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. 50479
    Prev
    Next
    INDEX
    Explanations

    periods of change

    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
     hopefully
    -0.12
    hopefully
    -0.10
    åı¯èĥ½
    -0.10
    ä¹Łåı¯èĥ½
    -0.09
    åı¯èĥ½ä¼ļ
    -0.09
    Hopefully
    -0.09
    åı¯èĥ½éľĢè¦ģ
    -0.08
    ä¹Łæľīåı¯èĥ½
    -0.08
     potentially
    -0.08
     probably
    -0.08
    POSITIVE LOGITS
     consistently
    0.10
     коÑĢÑĢ
    0.10
    è¯ģå®ŀåħ¶
    0.08
    çĶļèĩ³åľ¨
    0.08
     наблÑİдаеÑĤÑģÑı
    0.08
    å®ŀæµĭ
    0.08
    çĶļèĩ³æ¯Ķ
    0.08
    ç¡®æľī
    0.08
     addirittura
    0.08
     invariably
    0.08
    Activations Density 0.163%

    No Known Activations