© 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. 33429
    Prev
    Next
    INDEX
    Explanations

    time and complexity

    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
    å§Ĭ妹
    -0.08
     prematurely
    -0.08
    AuthProvider
    -0.08
    ubin
    -0.08
     odre
    -0.08
    æ··æIJŃ
    -0.08
    abr
    -0.08
    acam
    -0.07
    اخ
    -0.07
     ÑģоÑģ
    -0.07
    POSITIVE LOGITS
     negligible
    0.08
     tasks
    0.08
     overhead
    0.07
     anc
    0.07
    æµģ
    0.07
     computational
    0.07
     complexity
    0.07
    ime
    0.07
     computations
    0.07
    Tasks
    0.06
    Activations Density 0.025%

    No Known Activations