© 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. 27534
    Prev
    Next
    INDEX
    Explanations

    stopping criterion

    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
    ModelState
    -0.08
    ffel
    -0.08
    åIJ®
    -0.08
    æĿİä½³
    -0.07
     ModelState
    -0.07
    lical
    -0.07
    å°ıæŶåīį
    -0.07
    .Invariant
    -0.06
    ForObject
    -0.06
    åĿ¦
    -0.06
    POSITIVE LOGITS
    æľĢçŁŃ
    0.08
     stopping
    0.08
    onacci
    0.07
    -stop
    0.07
     оÑģÑĤанов
    0.07
    (stop
    0.07
    æ·¹
    0.07
     Bosco
    0.07
     elapsed
    0.07
    Elapsed
    0.07
    Activations Density 0.012%

    No Known Activations