© 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. 29962
    Prev
    Next
    INDEX
    Explanations

    spontaneously reduced

    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
    对äºİä¸ĢäºĽ
    -0.08
    PIO
    -0.08
    μÎŃÏĤ
    -0.07
    _cb
    -0.07
    ä¿®çļĦ
    -0.07
    ICODE
    -0.07
    ForObject
    -0.07
     Pik
    -0.06
    imensional
    -0.06
    è¿ĻäºĽåĽłç´ł
    -0.06
    POSITIVE LOGITS
     spontaneous
    0.08
    æŃ¢
    0.08
     spont
    0.08
     espont
    0.08
    æŃ»èĢħ
    0.08
     spontan
    0.07
    èĩªåıij
    0.07
     spontaneously
    0.07
    anking
    0.07
     chosen
    0.07
    Activations Density 0.001%

    No Known Activations