© 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. 24525
    Prev
    Next
    INDEX
    Explanations

    article 'a'

    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
    rie
    -0.07
    ÖĦ
    -0.07
    ottes
    -0.07
    orto
    -0.07
    æĹłæ¯Ķ
    -0.07
    egd
    -0.07
    好è¿IJ
    -0.07
    livet
    -0.07
     rar
    -0.07
    ãĥªãĥ¼ãĤ¹
    -0.06
    POSITIVE LOGITS
    auff
    0.07
    a
    0.07
    sequ
    0.07
     alike
    0.07
    ä¸Ģå¾ĭ
    0.07
    argo
    0.07
    å¾½
    0.06
    inkin
    0.06
    è¹
    0.06
    _terms
    0.06
    Activations Density 0.006%

    No Known Activations