© 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. 24792
    Prev
    Next
    INDEX
    Explanations

    known followed by specific nouns

    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
    管çIJĨæīĢ
    -0.08
    Ä«v
    -0.08
    ÙıÙħÙİÙij
    -0.08
    管çĶ¨
    -0.08
    lectual
    -0.08
    reven
    -0.08
    ĤŃ
    -0.07
    æīĢæ¶īåıĬ
    -0.07
    ä¸įéģİ
    -0.07
    CommandLine
    -0.07
    POSITIVE LOGITS
     already
    0.08
     precedent
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.07
     ÙĦدÙĬÙĨا
    0.07
    è¡Įä¸ļæłĩåĩĨ
    0.07
    æĻĵ
    0.06
     déjÃł
    0.06
    å·²ä¹ħçļĦ
    0.06
     known
    0.06
    azor
    0.06
    Activations Density 0.011%

    No Known Activations