© 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. 26000
    Prev
    Next
    INDEX
    Explanations

    fall under or belong to

    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
    rens
    -0.09
    els
    -0.08
    visor
    -0.08
    ÑįнеÑĢго
    -0.08
    以赴
    -0.08
    мок
    -0.08
    sters
    -0.08
    xel
    -0.08
    ivals
    -0.08
    bose
    -0.08
    POSITIVE LOGITS
    åħ¸åŀĭçļĦ
    0.10
    “
    0.10
    "
    0.08
    ä¸Ģç§į
    0.07
    :
    0.07
    åı¯ä»¥çļĦ
    0.07
    pecial
    0.07
    åĵªç§į
    0.06
    **
    0.06
    第äºĮç§į
    0.06
    Activations Density 0.002%

    No Known Activations