© 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. 19298
    Prev
    Next
    INDEX
    Explanations

    formation and suffixes

    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
    -0.07
    (
    -0.07
     (
    -0.06
    edis
    -0.06
    âĻ
    -0.06
    ï¼Ī
    -0.06
     '
    -0.06
    ذار
    -0.06
    天ä¹ĭ
    -0.06
    ighb
    -0.06
    POSITIVE LOGITS
    ÙĪÙĤÙĪÙģ
    0.09
    erties
    0.08
    Leaks
    0.08
    ÙĪÙĤÙĬ
    0.08
    &,
    0.08
    ifs
    0.08
    @d
    0.08
    ifers
    0.08
    Ïĥιά
    0.08
    IFS
    0.08
    Activations Density 0.013%

    No Known Activations