© 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. 39495
    Prev
    Next
    INDEX
    Explanations

    correct or right

    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
    åĴĮç»Ħç»ĩ
    -0.08
    éĢīæĭ©ä¸į
    -0.07
    å±ŀ
    -0.07
    ÅŁe
    -0.07
    avar
    -0.07
    åIJĮ声
    -0.07
    atak
    -0.07
    коÑĤ
    -0.07
    inha
    -0.07
    å¥ĩèīº
    -0.07
    POSITIVE LOGITS
    heits
    0.07
    issime
    0.07
    ÑģÑĤв
    0.07
    urga
    0.07
    ÃŃp
    0.07
    幡
    0.06
    umen
    0.06
    :
    0.06
    <![
    0.06
    ниÑĨ
    0.06
    Activations Density 0.005%

    No Known Activations