© 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. 27477
    Prev
    Next
    INDEX
    Explanations

    code block syntax

    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
    ujte
    -0.07
    udir
    -0.06
    ı
    -0.06
    blad
    -0.06
    -0.06
    (final
    -0.06
     (**
    -0.06
    (*
    -0.06
    项è§Ħå®ļ
    -0.06
    astra
    -0.06
    POSITIVE LOGITS
     [])
    0.08
     {})
    0.08
    ény
    0.08
    iasi
    0.07
    ãĥĥãĤ¯ãĤ¹
    0.07
    FromString
    0.07
    ())
    0.07
    ä½³
    0.07
    åIJĪéĽĨ
    0.07
    æľīä¸Ģå¥Ĺ
    0.07
    Activations Density 0.001%

    No Known Activations