© 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. 4045
    Prev
    Next
    INDEX
    Explanations

    flame retardant fabric

    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
    angez
    -0.08
    عÙħ
    -0.08
    ä¹Łä¸įå¿ħ
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    è¿ĺä¸įèĥ½
    -0.07
    пам
    -0.07
    åĬłåħ¥ä¹¦çŃ¾
    -0.07
    æĬĺä¸į
    -0.07
    uiltin
    -0.07
    ./.
    -0.07
    POSITIVE LOGITS
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.08
    è½¬çľ¼éĹ´
    0.07
    çİ°å°±
    0.07
    âĢIJ
    0.07
    以ä¸ĭæĺ¯å°ıç¼ĸ
    0.07
    æľ¬çĿĢ
    0.06
    çİ°å°Ĩ
    0.06
    çĴ¨
    0.06
    åĻľ
    0.06
    å§ĭèĩ³
    0.06
    Activations Density 0.052%

    No Known Activations