© 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. 63045
    Prev
    Next
    INDEX
    Explanations

    bar.bar1.bar2

    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
    ude
    -0.07
    tta
    -0.07
    anj
    -0.06
    uru
    -0.06
    æķĻ主
    -0.06
    绣ä¸Ģ
    -0.06
    oczy
    -0.06
    _generator
    -0.06
     *
    -0.06
    rops
    -0.06
    POSITIVE LOGITS
    óÅĤ
    0.08
     '~/
    0.08
    _GUI
    0.08
    psilon
    0.08
    èµģ
    0.07
    濯
    0.07
    使å®ĥ
    0.07
    estig
    0.07
    ESTE
    0.07
    ĮĢ
    0.07
    Activations Density 0.081%

    No Known Activations