© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48657
    Prev
    Next
    INDEX
    Explanations

    mathematical notations

    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
     Kushner
    -0.08
     Andersen
    -0.07
    olat
    -0.07
    å¤ķ
    -0.07
    cca
    -0.07
    UMMY
    -0.07
    åīį两
    -0.07
    çĺª
    -0.07
    .EX
    -0.06
    èĦī
    -0.06
    POSITIVE LOGITS
    ervers
    0.07
    lade
    0.07
    çļĦæ¸ħ
    0.07
    对æ¯Ķ
    0.07
    à¸Ħูà¹Ī
    0.07
    lerc
    0.07
    رز
    0.07
    ÑĢÑıз
    0.07
    ç´«æªĢ
    0.07
    vs
    0.07
    Activations Density 0.016%

    No Known Activations