© 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. 56383
    Prev
    Next
    INDEX
    Explanations

    period between or of

    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
    enticator
    -0.09
    à¹ī
    -0.09
    tienen
    -0.08
    ierarchy
    -0.08
    ustin
    -0.08
    pector
    -0.08
    ormsg
    -0.08
    urb
    -0.08
    ¹
    -0.08
    pected
    -0.08
    POSITIVE LOGITS
    ities
    0.09
    åĨħçļĦ
    0.09
    icals
    0.09
    ately
    0.09
    å±Ĭ满
    0.09
    ascal
    0.08
    haps
    0.08
    à¸Ļึà¸ĩ
    0.08
    åĪĩãĤĮ
    0.08
    åħ§çļĦ
    0.08
    Activations Density 0.066%

    No Known Activations