© 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. 18639
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and punctuation

    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
    olato
    -0.09
    /stream
    -0.08
    ocities
    -0.08
    пиÑĤа
    -0.08
    uster
    -0.08
    lington
    -0.08
    .Validation
    -0.08
    ennes
    -0.08
    æķĻä½ĵ
    -0.07
    ample
    -0.07
    POSITIVE LOGITS
    ³³³
    0.07
    bury
    0.06
    ³³
    0.06
    0.06
    ä¹İ
    0.06
    boo
    0.06
    ³³³³
    0.06
    <|box_end|>
    0.06
    èĢĮ对äºİ
    0.06
    ³³³³³³³
    0.06
    Activations Density 0.052%

    No Known Activations