© 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. 55634
    Prev
    Next
    INDEX
    Explanations

    groups, consumers, mice, year

    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
    éĶ¦ç»£
    -0.06
     ðŁij
    -0.06
    æĸŃéĿ¢
    -0.06
    åĭĺ
    -0.06
    æĸĮ
    -0.06
    æ£Ĵ
    -0.06
    ħ
    -0.06
     ðŁ
    -0.06
    eff
    -0.06
    _eff
    -0.06
    POSITIVE LOGITS
     inoltre
    0.12
     insomma
    0.11
    ä¹Łæ¯Ķ
    0.11
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.10
    ä¹Łå¹¶éĿŀ
    0.10
     tampoco
    0.09
     ayrıca
    0.09
    æī©å±ķèµĦæĸĻ
    0.09
     tambien
    0.09
     também
    0.09
    Activations Density 0.289%

    No Known Activations