© 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. 22021
    Prev
    Next
    INDEX
    Explanations

    designed for

    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
    ä¸įæķ£
    -0.08
     ilÃŃc
    -0.07
    ingin
    -0.07
    gefähr
    -0.07
    ungk
    -0.07
    åħĢ
    -0.07
     actionable
    -0.07
    è°£
    -0.07
    inary
    -0.07
    _PREF
    -0.07
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.09
     designed
    0.09
    å¾Ģå¾Ģæĺ¯
    0.08
    Designed
    0.08
    prior
    0.08
     often
    0.08
     deliberately
    0.08
    æĽ´æ³¨éĩį
    0.08
     lacks
    0.08
     Designed
    0.08
    Activations Density 0.127%

    No Known Activations