© 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. 28712
    Prev
    Next
    INDEX
    Explanations

    mathematical properties and relations

    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
    osen
    -0.08
    亦æĪĸæĺ¯
    -0.08
    æĪĸå¤ļ个
    -0.07
     Parall
    -0.07
     frau
    -0.07
    FOUND
    -0.07
    佳人
    -0.07
    <?>
    -0.07
    ambang
    -0.07
    หà¸Ļà¹Īà¸Ńย
    -0.07
    POSITIVE LOGITS
    çļĦæĦıæĢĿæĺ¯
    0.07
    è¿ĻæĦıåij³çĿĢ
    0.07
    åĽłæŃ¤åľ¨
    0.07
     except
    0.07
    å°±æĺ¯è¯´
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.07
    榴
    0.06
    åĽłæѤ
    0.06
    except
    0.06
     among
    0.06
    Activations Density 0.015%

    No Known Activations