© 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. 61557
    Prev
    Next
    INDEX
    Explanations

    legal writings and orders

    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
    _trim
    -0.08
    tourn
    -0.08
    trimmed
    -0.08
    bero
    -0.08
    accia
    -0.08
     Valenci
    -0.07
    Intent
    -0.07
    ī½
    -0.07
    ÑĢÑĥбе
    -0.07
    æķ°ä¸įæ¸ħ
    -0.07
    POSITIVE LOGITS
    åīįæıIJæĺ¯
    0.12
    çļĦåīįæıIJ
    0.11
     assumes
    0.09
    åı¯éĿłçļĦ
    0.09
    åīįæıIJ
    0.09
     assumed
    0.09
     reliable
    0.09
     fiable
    0.09
     assumption
    0.08
     Assumes
    0.08
    Activations Density 0.041%

    No Known Activations