© 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. 2363
    Prev
    Next
    INDEX
    Explanations

    http://

    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
    ¼
    -0.08
     pressi
    -0.08
    ments
    -0.08
    ãģ£ãģįãĤĬ
    -0.07
    мини
    -0.07
    çĮ©çĮ©
    -0.07
    ermen
    -0.07
    ombie
    -0.07
    να
    -0.07
    üle
    -0.07
    POSITIVE LOGITS
    eenth
    0.09
    :\/\/
    0.09
    ://
    0.08
    ation
    0.08
    sson
    0.08
    خر
    0.08
    retty
    0.08
    itude
    0.08
    ree
    0.08
    ness
    0.07
    Activations Density 0.135%

    No Known Activations