© 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. 7726
    Prev
    Next
    INDEX
    Explanations

    Module, circuits, detection, aspiration, query, SI, diamagnetism

    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
    çĥŃéŨæݨèįIJ
    -0.10
    <|endoftext|>
    -0.10
    æľĢæĸ°åıijå¸ĥ
    -0.09
    <|file_sep|>
    -0.08
     (("
    -0.07
    æľ¬æĸĩæĿ¥èĩª
    -0.07
    ;amp
    -0.07
    çļĦä¸ĵæłı
    -0.07
     пÑĢио
    -0.07
     ÑĥпÑĢо
    -0.06
    POSITIVE LOGITS
    >>>>>>>
    0.12
    <|fim_suffix|>
    0.12
    č↵↵
    0.10
    <|im_end|>
    0.09
    Dettagli
    0.09
    åĨĩæľī
    0.08
     ___
    0.08
     \"
    0.08
    ADVERTISEMENT
    0.08
    		  ↵
    0.08
    Activations Density 97.512%

    No Known Activations