© 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. 64074
    Prev
    Next
    INDEX
    Explanations

    oxygen or O followed by a number or 'and'

    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
    пÑĢоÑĨе
    -0.08
    вÑĤÑĢа
    -0.07
    ä¼Ļ
    -0.07
    еÑĢбÑĥ
    -0.07
    å¸ħæ°ĶçļĦ
    -0.07
    æ¶Ī磨
    -0.07
    ÑģовеÑģÑĤ
    -0.07
    å¸ħæ°Ķ
    -0.06
    orique
    -0.06
    éĺ³æĢ§
    -0.06
    POSITIVE LOGITS
    xygen
    0.11
    esson
    0.09
    vim
    0.09
    vertime
    0.08
    ceans
    0.08
    lymp
    0.08
    egov
    0.08
    å²IJ
    0.08
    imbus
    0.08
    itura
    0.08
    Activations Density 0.009%

    No Known Activations