© 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. 26977
    Prev
    Next
    INDEX
    Explanations

    no change or removal

    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
    æŃ¤èµ·
    -0.08
    jaman
    -0.07
    ä¸įæĢĿ
    -0.07
     оÑĩеÑĢед
    -0.07
    _DIAG
    -0.07
    ayette
    -0.07
    æĸ°ä¸ĸ纪
    -0.07
    ffin
    -0.07
    ired
    -0.07
    gire
    -0.07
    POSITIVE LOGITS
     underlying
    0.08
    èĸ
    0.07
    occ
    0.07
     afterward
    0.07
     intact
    0.07
    å®Įæķ´çļĦ
    0.07
    å®Įæķ´
    0.06
    ä¿ĿçķĻ
    0.06
     fully
    0.06
    太å¤ļçļĦ
    0.06
    Activations Density 0.141%

    No Known Activations