© 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. 42045
    Prev
    Next
    INDEX
    Explanations

    finding numbers or words

    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
     tzw
    -0.08
     tzv
    -0.08
    pia
    -0.08
    ä¾Ŀæīĺ
    -0.08
    éĴ§
    -0.08
     ugyanis
    -0.07
    èĩªåľ¨
    -0.07
    æĶ¾åľ¨äºĨ
    -0.07
     Quit
    -0.07
    æĪijåľĭ
    -0.07
    POSITIVE LOGITS
    0.09
    ä¸į幸
    0.07
    èĪ¬åľ°
    0.07
    éļ¾ä»¥ç½®ä¿¡
    0.07
    çļĦæľĭåıĭ们
    0.06
    è¿Ļå°Ĩ
    0.06
     normalerweise
    0.06
    请æĭ¨æīĵ
    0.06
    åĤij
    0.06
    èĭ±å¯¸
    0.06
    Activations Density 0.292%

    No Known Activations