© 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. 62817
    Prev
    Next
    INDEX
    Explanations

    EDIT after numbers or 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
    roke
    -0.07
    oki
    -0.07
    代ä¼ļ
    -0.07
    formed
    -0.07
    产çĶŁçļĦ
    -0.07
    å½¢æĪIJçļĦ
    -0.06
     Plen
    -0.06
    ä¸ĢæŦåĩºçİ°
    -0.06
    ÙĪÙģ
    -0.06
     produced
    -0.06
    POSITIVE LOGITS
    zah
    0.07
    ithe
    0.07
    enberg
    0.07
    zte
    0.07
     Vul
    0.07
    iach
    0.07
    azier
    0.07
    zend
    0.07
    isse
    0.07
    ivant
    0.07
    Activations Density 0.019%

    No Known Activations