© 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. 15738
    Prev
    Next
    INDEX
    Explanations

    technical completion and description

    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
    itari
    -0.07
    çļ
    -0.07
    upal
    -0.06
    aiser
    -0.06
    ração
    -0.06
     ($.
    -0.06
    bir
    -0.06
    irman
    -0.06
     Trag
    -0.06
    ãĤ³ãĥ¢
    -0.06
    POSITIVE LOGITS
    .Word
    0.08
    åĭĩå¾Ģ缴åīį
    0.08
    åĽŃè·¯
    0.08
    æĪijåij¢
    0.07
    é¨
    0.07
    oca
    0.07
    enzen
    0.07
    otis
    0.07
    رب
    0.07
    continu
    0.07
    Activations Density 0.021%

    No Known Activations