© 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. 50493
    Prev
    Next
    INDEX
    Explanations

    prime factors of

    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
     euth
    -0.08
     #@
    -0.07
    æ
    -0.07
    yto
    -0.07
     Linden
    -0.07
    दन
    -0.07
    龸çİĭ
    -0.07
    æŁ¥çľĭåħ¨æĸĩ
    -0.07
    edy
    -0.07
    æī¦
    -0.07
    POSITIVE LOGITS
    asma
    0.09
     Pase
    0.07
     جÙĩØ©
    0.07
    _pool
    0.06
    aza
    0.06
     Bari
    0.06
    å¿ħ
    0.06
     lari
    0.06
     quyá»ĥn
    0.06
    éĹª
    0.06
    Activations Density 0.005%

    No Known Activations