© 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. 17460
    Prev
    Next
    INDEX
    Explanations

    bloc nations, rehab, pathologist, pocket, bins, documents, house, computer

    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
    !!!!!!!!
    -0.09
    æī©å±ķèµĦæĸĻ
    -0.08
    å¦Ĥæ¶īåıĬ
    -0.08
    alha
    -0.08
     übrigens
    -0.08
    对ä¸Ĭè¿°
    -0.08
    !!!!!
    -0.08
    åľ¨ä¸Ĭè¿°
    -0.07
     inoltre
    -0.07
     aforementioned
    -0.07
    POSITIVE LOGITS
    endis
    0.08
    对åIJ§
    0.07
     ndr
    0.07
    èĢĮå¾ĹåIJį
    0.06
    ato
    0.06
    è¡Įéģĵ
    0.06
    ub
    0.06
    åį´ä¸Ģ缴
    0.06
    ä¸ĭéĿ¢æĺ¯å°ıç¼ĸ
    0.06
    ump
    0.06
    Activations Density 0.639%

    No Known Activations