© 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. 51266
    Prev
    Next
    INDEX
    Explanations

    far from or beyond

    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
    richt
    -0.09
    halle
    -0.09
    ات
    -0.09
    -wow
    -0.08
    âĵĴ
    -0.08
    eer
    -0.08
    اتÙĬ
    -0.08
    ighton
    -0.08
    uality
    -0.08
    eeper
    -0.08
    POSITIVE LOGITS
    thest
    0.17
    ness
    0.12
    -reaching
    0.12
    à¹Ĩ
    0.10
    mland
    0.09
     sekali
    0.09
    à¹Ģà¸ģิà¸Ļà¹Ħà¸Ľ
    0.08
    (er
    0.08
    ings
    0.08
     enough
    0.08
    Activations Density 0.032%

    No Known Activations