© 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. 50716
    Prev
    Next
    INDEX
    Explanations

    this and it are

    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
     elsewhere
    -0.08
    çĶŁæ´»ä¸Ĭ
    -0.07
     nearby
    -0.07
     ÙĦاØŃÙĤ
    -0.07
    imilar
    -0.07
     called
    -0.06
    ä¸Ģ个æĺ¯
    -0.06
     Ñħод
    -0.06
    /misc
    -0.06
    å°ıå°Ĩ
    -0.06
    POSITIVE LOGITS
    çļĦåIJĮæŶ
    0.10
    åIJĮæĹ¶ä¹Łè¦ģ
    0.09
    åIJĮæŶè¿ĺè¦ģ
    0.09
     regardless
    0.08
     WITHOUT
    0.08
     irrespective
    0.08
    åIJĮæŶ
    0.08
     accompanied
    0.08
    åIJĮæŶè¿ĺ
    0.08
    ãģ¤ãģ¤
    0.08
    Activations Density 0.504%

    No Known Activations