© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11128
    Prev
    Next
    INDEX
    Explanations

    semigroup, kernels, probability, Licensed, Copyright

    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
     Capitals
    -0.07
    å¤ĩæĪĺ
    -0.07
    è°ĥéĢŁ
    -0.07
     bis
    -0.07
     bowling
    -0.06
    ingk
    -0.06
    çºł
    -0.06
    æĪ¿ç§Ł
    -0.06
    à¤ĸा
    -0.06
     owner
    -0.06
    POSITIVE LOGITS
    -distance
    0.09
    distance
    0.09
    _DISTANCE
    0.08
     lej
    0.08
     Distance
    0.08
     distance
    0.08
    éļĶ
    0.08
    å»¶è¿Ł
    0.08
    Distance
    0.08
    è·ĿéĽ¢
    0.08
    Activations Density 0.011%

    No Known Activations