© 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. 32684
    Prev
    Next
    INDEX
    Explanations

    tibiotalar osteotomy

    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
    ulk
    -0.08
    rix
    -0.08
    dek
    -0.08
    кÑĥÑĢа
    -0.07
    обе
    -0.07
    å¤ĸå±Ĥ
    -0.07
    Thunk
    -0.07
    agine
    -0.07
    ancell
    -0.07
    åħĥå®Ŀ
    -0.07
    POSITIVE LOGITS
     â
    0.07
     �
    0.06
     zod
    0.06
    çļĦè¿Ļä¸Ģ
    0.06
    çļĦæķ°æį®
    0.06
    æĿijæĿijæ°ij
    0.06
     Parkway
    0.06
    æŁ»
    0.06
    æķı
    0.06
    便è¦ģ
    0.06
    Activations Density 0.446%

    No Known Activations