© 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. 64956
    Prev
    Next
    INDEX
    Explanations

    so-called or termed phrases

    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
    æł¸éħ¸
    -0.08
    çļĭ
    -0.08
    abble
    -0.08
    nonnull
    -0.07
    Attrs
    -0.07
    éŨä¸ĭ
    -0.07
    pher
    -0.07
    anu
    -0.07
    ÑĢаÑĤа
    -0.07
    èĩ³åħ³
    -0.07
    POSITIVE LOGITS
     tzv
    0.12
    æīĢè°ĵçļĦ
    0.11
     tzw
    0.10
     cosidd
    0.10
     sogenannten
    0.10
     sogenannte
    0.10
    æīĢè¬ĤçļĦ
    0.09
     "
    0.09
    åı«åģļ
    0.09
    çŃīçݰ象
    0.08
    Activations Density 0.327%

    No Known Activations