© 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. 50399
    Prev
    Next
    INDEX
    Explanations

    form or produce

    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
    ëĦĪ
    -0.07
    éĽį
    -0.07
    Catch
    -0.07
    à¸ĩ
    -0.06
    Disconnect
    -0.06
    éĩĮéĿ¢æľī
    -0.06
    /cs
    -0.06
    utos
    -0.06
    ä¼´
    -0.06
    çļĦä¸Ģ项éĩįè¦ģ
    -0.06
    POSITIVE LOGITS
    åĪ¶æĪIJ
    0.09
     resulting
    0.09
     yielding
    0.09
     yields
    0.09
    åĨĻæĪIJ
    0.08
    ç»ĵæŀľæĺ¯
    0.08
     ergibt
    0.08
     yield
    0.08
    ç»ĵæŀľä¸º
    0.08
    Ñħодом
    0.08
    Activations Density 0.108%

    No Known Activations