© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    AUstralia, DIGital, PENnsylvania

    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
    ENCED
    -0.07
    Advertisements
    -0.06
    à¹īà¸Ńม
    -0.06
    adors
    -0.06
    annies
    -0.06
    icionados
    -0.06
    ónicas
    -0.06
    askets
    -0.06
    amenta
    -0.06
    ATORS
    -0.06
    POSITIVE LOGITS
    nger
    0.10
    ir
    0.09
    yer
    0.09
    ier
    0.09
    our
    0.09
    æľ¬å¸ĸ
    0.08
    ern
    0.08
    uit
    0.08
    ithe
    0.08
    here
    0.08
    Activations Density 1.529%

    No Known Activations