© 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. 34210
    Prev
    Next
    INDEX
    Explanations

    useful

    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
    etype
    -0.09
    izens
    -0.09
    etat
    -0.09
    æľĪä¸Ĭ
    -0.09
    ηÏĥη
    -0.09
    izen
    -0.09
    amat
    -0.08
    ebol
    -0.08
    upati
    -0.08
    ấp
    -0.08
    POSITIVE LOGITS
    -looking
    0.12
    ÃŃsima
    0.11
     جداÙĭ
    0.11
     جدÙĭا
    0.11
     banget
    0.10
    ly
    0.10
     ÙĦÙĦغاÙĬØ©
    0.09
    ÃŃsimo
    0.09
    fully
    0.09
     جدا
    0.09
    Activations Density 0.061%

    No Known Activations