© 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. 7752
    Prev
    Next
    INDEX
    Explanations

    is saying

    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
    åĽłä¸ºåħ¶
    -0.07
    лед
    -0.07
    并ä¸Ķåľ¨
    -0.07
    anic
    -0.07
    mér
    -0.07
    acing
    -0.06
    imately
    -0.06
    ields
    -0.06
    ajo
    -0.06
    aned
    -0.06
    POSITIVE LOGITS
    ä¹Łåı¯èĥ½
    0.09
    ä¹Łè®¸
    0.09
    并ä¸įæĺ¯
    0.08
    à¹Ħมà¹Īà¹Ħà¸Ķà¹ī
    0.08
    ä¹Łåı¯èĥ½æĺ¯
    0.08
    ä¹Łæľīåı¯èĥ½
    0.08
    æľªå¿ħ
    0.08
    åĪ°åºķæĺ¯
    0.08
    ãĤĤãģĹãģĭ
    0.08
    çĻĸ
    0.08
    Activations Density 0.018%

    No Known Activations