© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 24639
    Prev
    Next
    INDEX
    Explanations

    answer to questions or questions requiring answers

    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
    raries
    -0.10
    leszt
    -0.09
    resh
    -0.09
    irão
    -0.09
    nitz
    -0.08
    arts
    -0.08
    ãģªãĤīãģļ
    -0.08
    ÙĬاÙĨ
    -0.08
    RARY
    -0.08
    ä¸Ĭéĺµ
    -0.08
    POSITIVE LOGITS
    able
    0.09
    steller
    0.08
    er
    0.08
    iable
    0.08
    ÑĮÑĤе
    0.07
    ÏĦηÏĥη
    0.07
    eri
    0.07
    ter
    0.07
    sto
    0.07
    ment
    0.07
    Activations Density 0.033%

    No Known Activations