© 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. 41972
    Prev
    Next
    INDEX
    Explanations

    experimental results and tests

    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
    å¥ĩ
    -0.07
    adox
    -0.07
    èĥ½è¢«
    -0.06
    æŀļ
    -0.06
    ä¸įèĥ½è¢«
    -0.06
    ÄĻd
    -0.06
    被人们
    -0.06
     odd
    -0.06
    agno
    -0.06
     sovere
    -0.06
    POSITIVE LOGITS
    results
    0.11
    æµĭè¯ķç»ĵæŀľ
    0.10
    /results
    0.10
     results
    0.10
     comparisons
    0.10
    _results
    0.10
    ç»ĵæŀľè¡¨æĺİ
    0.10
    è¯ģå®ŀåħ¶
    0.10
     tests
    0.09
    Results
    0.09
    Activations Density 0.263%

    No Known Activations