© 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. 61530
    Prev
    Next
    INDEX
    Explanations

    then a colon

    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
    kid
    -0.07
    enix
    -0.07
    èĮľ
    -0.06
    .measure
    -0.06
    apis
    -0.06
     thereof
    -0.06
    ׳×ĵ
    -0.05
    /ref
    -0.05
    xies
    -0.05
    itol
    -0.05
    POSITIVE LOGITS
    arki
    0.09
    Ïīμα
    0.08
    arkin
    0.08
    ä½łçļĦ人
    0.08
    ëĭĮ
    0.08
    ª
    0.07
    iefert
    0.07
    æµ®çĶŁ
    0.07
    à¹Ģà¸Ĭà¹Īà¸Ļà¸ģัà¸Ļ
    0.07
    AAC
    0.07
    Activations Density 0.054%

    No Known Activations