© 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. 1807
    Prev
    Next
    INDEX
    Explanations

    words ending in 'able' or 'ing' after certain tokens

    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
    æīĢ幸
    -0.08
    reto
    -0.08
    isco
    -0.08
     overe
    -0.07
    uco
    -0.07
    αιο
    -0.07
    HeaderValue
    -0.07
    å·²ç»ıåĪ°äºĨ
    -0.07
     Tuc
    -0.07
    ekin
    -0.07
    POSITIVE LOGITS
    ä¸ĢèĪ¬æĿ¥è¯´
    0.09
    åİŁåĪĻä¸Ĭ
    0.08
    ä¸ĢèĪ¬èĢĮè¨Ģ
    0.08
    æĪĸèĢħæľī
    0.07
    å¾Ģå¾Ģæĺ¯
    0.07
    å¤įåĪ¶æĪĸ
    0.07
    åĩ¡æĺ¯
    0.07
     Generally
    0.07
    çŃīåĽłç´ł
    0.07
     generally
    0.07
    Activations Density 0.061%

    No Known Activations