© 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. 32327
    Prev
    Next
    INDEX
    Explanations

    IP address information

    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
    vos
    -0.07
    è³ŀ
    -0.07
    ä¸Ĭæ·»
    -0.07
    åıįåºĶçļĦ
    -0.07
    æī§æ³ķæ£ĢæŁ¥
    -0.07
    ellini
    -0.07
    rÃł
    -0.07
    ãĥĥãĤ«
    -0.07
     Xô
    -0.07
    产åĵģä»·æł¼
    -0.07
    POSITIVE LOGITS
    ÑĢод
    0.08
    ovable
    0.08
    èī²åĪĹ
    0.06
    åĩºæīĭ
    0.06
     bet
    0.06
    rod
    0.06
    oval
    0.06
    ষà§įà¦ł
    0.06
    æĮģæľīçļĦ
    0.06
    _gp
    0.06
    Activations Density 0.001%

    No Known Activations