© 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. 13716
    Prev
    Next
    INDEX
    Explanations

    unicode punctuation and numbers

    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
    åĬªåĬĽåģļåĪ°
    -0.08
    atype
    -0.07
     misc
    -0.07
    OrCreate
    -0.07
     alc
    -0.07
    åѦå¾Ĵ
    -0.07
    ä¸Ģåıį
    -0.06
    ä¸įåIJĮç±»åŀĭçļĦ
    -0.06
    alle
    -0.06
    èĩªèº«é£İéĻ©
    -0.06
    POSITIVE LOGITS
     reint
    0.09
    inded
    0.07
    ç»ħ
    0.07
    estre
    0.07
    å¼ķéĢ²
    0.07
     reinst
    0.07
    oggle
    0.07
     îm
    0.07
    ä¾Ŀä¾Ŀ
    0.07
    å¼ķè¿ĽäºĨ
    0.07
    Activations Density 0.002%

    No Known Activations