© 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. 28367
    Prev
    Next
    INDEX
    Explanations

    explicitly required

    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
    emas
    -0.08
     certainly
    -0.07
    asl
    -0.07
     surely
    -0.07
    æĹłæĦ§
    -0.07
    表示äºĨ
    -0.07
    utow
    -0.07
    çĶĺå¿ĥ
    -0.07
    常说çļĦ
    -0.07
    _TD
    -0.07
    POSITIVE LOGITS
     challenging
    0.08
    误导
    0.08
     explicitly
    0.08
    æĺİç¡®è¦ģæ±Ĥ
    0.08
    éļIJèĹıåľ¨
    0.08
    Explicit
    0.08
     explicit
    0.08
    并è¦ģæ±Ĥ
    0.07
    fusc
    0.07
     deliberately
    0.07
    Activations Density 0.017%

    No Known Activations