© 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. 40135
    Prev
    Next
    INDEX
    Explanations

    marks or breaks in text

    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
     ,
    -0.07
    reo
    -0.06
    atty
    -0.06
    irected
    -0.06
    asing
    -0.06
    FORT
    -0.06
    èĽ
    -0.06
    ijas
    -0.06
    åĬŀå®ŀäºĭ
    -0.06
     ÑĥÑĩ
    -0.06
    POSITIVE LOGITS
    venir
    0.09
    UNET
    0.08
    éĢļè¿ĩå¼Ģå±ķ
    0.08
    tober
    0.08
    alise
    0.08
    alai
    0.07
    ÙĪÙĨدÙĩ
    0.07
    eira
    0.07
    leep
    0.07
    riba
    0.07
    Activations Density 0.011%

    No Known Activations