© 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. 8403
    Prev
    Next
    INDEX
    Explanations

    shapes and structures

    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
     proxies
    -0.07
     tainted
    -0.07
     trickle
    -0.07
    åı¯éĿł
    -0.07
     trusted
    -0.06
    ä¸Ģéģĵ
    -0.06
    ä¿¡ä»»
    -0.06
    å¾®éĩı
    -0.06
    èµ
    -0.06
     trustworthy
    -0.06
    POSITIVE LOGITS
    è§Ĩè§īä¸Ĭ
    0.11
    å½¢æħĭ
    0.11
    stype
    0.11
    å½¢æĢģ
    0.10
     formations
    0.10
     اÙĦØ´ÙĥÙĦ
    0.10
    attern
    0.10
    å½¢çĬ¶
    0.10
    å½¢çĬ¶çļĦ
    0.10
     morphology
    0.10
    Activations Density 0.190%

    No Known Activations