© 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. 27918
    Prev
    Next
    INDEX
    Explanations

    metadata attributes and properties

    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
    chon
    -0.07
    oons
    -0.07
    LEC
    -0.07
     central
    -0.07
    hare
    -0.07
    pati
    -0.07
     Daly
    -0.07
    agak
    -0.07
    amani
    -0.07
    _ajax
    -0.07
    POSITIVE LOGITS
     additions
    0.09
    -extra
    0.09
     extras
    0.08
    éĻĦåĬł
    0.08
    /tags
    0.08
     tambahan
    0.08
    个æĢ§
    0.08
    Extras
    0.08
     коÑĤоÑĢÑĭми
    0.07
    Applied
    0.07
    Activations Density 0.214%

    No Known Activations