© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11866
    Prev
    Next
    INDEX
    Explanations

    correct statements or status

    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
    rans
    -0.08
    INLINE
    -0.08
    unno
    -0.08
    ÑĻе
    -0.07
    æĢİæł·æīįèĥ½
    -0.07
     NIL
    -0.07
    MLS
    -0.07
    ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»ãĥ»
    -0.07
    æľĢ大ç¨ĭ度
    -0.07
    _poll
    -0.07
    POSITIVE LOGITS
    æĺ¯åIJ¦æŃ£ç¡®
    0.15
    æĺ¯æŃ£ç¡®çļĦ
    0.14
    ç¡®å®ŀ
    0.13
    確ãģĭãģ«
    0.13
    æŃ£ç¡®çļĦ
    0.12
     correctly
    0.12
    ç¡®å®ŀæĺ¯
    0.12
    æĺ¯å¯¹çļĦ
    0.12
     indeed
    0.12
     correct
    0.11
    Activations Density 0.017%

    No Known Activations