© 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. 9524
    Prev
    Next
    INDEX
    Explanations

    whitespace and spaces

    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
    ücks
    -0.08
    outed
    -0.08
    ä¸įæį¢
    -0.08
    ساب
    -0.07
    SHOT
    -0.07
    æ½¼
    -0.07
    æļĤæĹł
    -0.07
    OrUpdate
    -0.07
    å¤§æľ¬
    -0.07
    大åij¼
    -0.07
    POSITIVE LOGITS
    è·³è¿ĩ
    0.07
    ä¸įèĥ½ä½ľä¸º
    0.06
    -
    0.06
    kü
    0.06
    kes
    0.06
     cul
    0.06
    æ·±è¿ľ
    0.06
    åıĪä¸įæĺ¯
    0.06
     ubiquitous
    0.06
    nad
    0.06
    Activations Density 0.002%

    No Known Activations