© 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. 39372
    Prev
    Next
    INDEX
    Explanations

    category or categories

    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
    ly
    -0.09
    ened
    -0.08
    baugh
    -0.08
    ness
    -0.08
    erval
    -0.08
    à¸Ĺà¹Į
    -0.07
    dater
    -0.07
    سر
    -0.07
    ivals
    -0.07
    Toolkit
    -0.07
    POSITIVE LOGITS
     بÙĨدÛĮ
    0.09
    ifornia
    0.08
    à¹Īà¸ĩ
    0.08
    oodoo
    0.08
    icals
    0.08
    -wide
    0.08
    åĨħçļĦ
    0.08
    lobals
    0.08
    apult
    0.07
    wide
    0.07
    Activations Density 0.084%

    No Known Activations