© 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. 4359
    Prev
    Next
    INDEX
    Explanations

    position or dimensions (x, y, offset)

    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
    obe
    -0.07
     deactivate
    -0.07
    ÐľÐļ
    -0.07
    ترÙħ
    -0.07
    вÑĢо
    -0.07
    erer
    -0.07
    .nodeType
    -0.07
    antal
    -0.07
     types
    -0.07
    رÙģ
    -0.07
    POSITIVE LOGITS
     offset
    0.09
    å§ĭ
    0.09
    offset
    0.08
    èµ·å§ĭ
    0.08
    å¼Ģå§ĭçļĦ
    0.08
    .offset
    0.08
    OFFSET
    0.08
    åģı移
    0.08
    	offset
    0.08
     Cum
    0.08
    Activations Density 0.104%

    No Known Activations