© 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. 15010
    Prev
    Next
    INDEX
    Explanations

    order of degree

    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
    NotAllowed
    -0.08
    segn
    -0.08
    ä¸įå¾ĹäºĨ
    -0.08
    дÑĥма
    -0.07
    ullan
    -0.07
    oga
    -0.07
    gle
    -0.07
    å·¥ä½ľçļĦåIJĮæŶ
    -0.07
    -Sep
    -0.07
    Į
    -0.07
    POSITIVE LOGITS
    åħ³äºİ
    0.07
     regarding
    0.07
    0.07
    UpdatedAt
    0.06
    æľīä¸ĭåĪĹ
    0.06
    åıĤæķ°
    0.06
    ÄĻb
    0.06
    unto
    0.06
     about
    0.06
    å£
    0.06
    Activations Density 0.086%

    No Known Activations