© 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. 33546
    Prev
    Next
    INDEX
    Explanations

    research by

    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
    à¹ĥà¸Ī
    -0.09
    ÑģÑı
    -0.09
    ities
    -0.09
    áĥ£áĥłáĥĺ
    -0.08
     بÙĨدÛĮ
    -0.08
    Ñģпол
    -0.08
    tering
    -0.08
    NESS
    -0.08
    wner
    -0.08
    arity
    -0.08
    POSITIVE LOGITS
    er
    0.11
    ered
    0.10
    es
    0.08
    erer
    0.08
    ellers
    0.08
    eves
    0.08
    åĪ°çļĦ
    0.08
    ாள
    0.08
    erst
    0.08
    eres
    0.07
    Activations Density 0.049%

    No Known Activations