© 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. 65317
    Prev
    Next
    INDEX
    Explanations

    stain finishing color fade

    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
     dangerous
    -0.07
    åį±éĻ©çļĦ
    -0.07
    çł´ç¢İ
    -0.07
     parach
    -0.07
    æĶ¹ç¼ĸ
    -0.07
    ç¡®ä¿Ŀå®īåħ¨
    -0.07
     pelvic
    -0.07
    åį±éĻ©
    -0.06
     compr
    -0.06
     dangere
    -0.06
    POSITIVE LOGITS
    æ¯ĽåŃĶ
    0.09
    纹çIJĨ
    0.09
    inks
    0.09
     dauerhaft
    0.09
    æ°¸ä¹ħæĢ§
    0.08
    æĹ¥åIJİ
    0.08
     thẩm
    0.08
    fade
    0.08
    Owners
    0.08
     vĩnh
    0.08
    Activations Density 0.057%

    No Known Activations