© 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. 49357
    Prev
    Next
    INDEX
    Explanations

    relevant words

    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
    æĥ³æĸ¹
    -0.09
    zerw
    -0.08
    éĢ»è¾ijæĢĿç»´
    -0.07
    ç»ıä¿¡
    -0.07
    飦
    -0.07
    æĪijèĩªå·±
    -0.07
    ä¸įå®ĮçļĦ
    -0.07
    лак
    -0.07
    åľ¨ä»»ä½ķ
    -0.07
    åľ¨éĿŀ
    -0.07
    POSITIVE LOGITS
     relevant
    0.13
    relevant
    0.11
     Relevant
    0.10
     relevante
    0.10
    levant
    0.09
     pertinent
    0.09
     relevantes
    0.09
     pertinentes
    0.08
     pertinente
    0.08
     relevan
    0.08
    Activations Density 0.152%

    No Known Activations