© 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. 26775
    Prev
    Next
    INDEX
    Explanations

    function notation f(x)

    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
    æ³ķæĺ¯
    -0.06
    ellino
    -0.06
    æ³ķçŃī
    -0.06
    trate
    -0.06
    å°ĶèĴĻ
    -0.06
    ings
    -0.06
    ÑĥÑĩ
    -0.06
    ãģ¦
    -0.06
    ail
    -0.06
    æħĪ
    -0.06
    POSITIVE LOGITS
    enix
    0.08
    оÑĢо
    0.08
    arning
    0.07
    ahoma
    0.07
    æ²ĥæĸ¯
    0.07
     Pró
    0.07
    æŃ¤åľ°
    0.07
    vore
    0.07
    auge
    0.07
     quals
    0.07
    Activations Density 0.012%

    No Known Activations