© 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. 1299
    Prev
    Next
    INDEX
    Explanations

    introducing new species, methods, or versions

    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
    åıijå±ķçļĦéľĢè¦ģ
    -0.07
    ogn
    -0.07
    çªģå¦Ĥåħ¶
    -0.07
    ç»Ī究
    -0.07
    äºĭåıĺ
    -0.07
    æĹłå¤Ħ
    -0.06
    ä¸ĭéĿ¢æĺ¯
    -0.06
    çļĦä»»ä½ķ
    -0.06
    æīĵåĵį
    -0.06
    artis
    -0.06
    POSITIVE LOGITS
    åı«åģļ
    0.15
    åIJį为
    0.12
     called
    0.12
    称ä¹ĭ为
    0.11
    称为
    0.11
    ç§°ä½ľ
    0.11
    åı«
    0.11
     bernama
    0.11
    åIJįåı«
    0.11
    åij½åIJį为
    0.11
    Activations Density 0.765%

    No Known Activations