© 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. 41393
    Prev
    Next
    INDEX
    Explanations

    handling spaces and quotes

    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
    å°º
    -0.08
    ç·£
    -0.08
     [('
    -0.08
    å¾Ĵ
    -0.08
     marginal
    -0.08
    вел
    -0.08
    estig
    -0.08
    antemente
    -0.08
    ulin
    -0.07
    ç¼ĺ
    -0.07
    POSITIVE LOGITS
     escaped
    0.08
    UNCT
    0.07
     escapes
    0.07
     text
    0.07
    éģ¿
    0.07
    大çİĭ
    0.07
    ä¸įæĢķ
    0.07
     unint
    0.07
     escaping
    0.06
    QUOTE
    0.06
    Activations Density 0.146%

    No Known Activations