© 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. 22406
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
    åĴ³åĴ³
    -0.10
     ugyanis
    -0.09
    onti
    -0.09
    æľ¬ç«ĻåĨħ容
    -0.09
    ëĭĪëĭ¤
    -0.08
    unesse
    -0.08
    erstand
    -0.08
     mantu
    -0.08
    ấn
    -0.08
    chemist
    -0.08
    POSITIVE LOGITS
    ↵↵
    0.06
    acle
    0.06
    ÙĥÙī
    0.06
    0.06
    ation
    0.06
     (
    0.06
    adh
    0.05
    ara
    0.05
    s
    0.05
     Ken
    0.05
    Activations Density 0.006%

    No Known Activations