© 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. 30450
    Prev
    Next
    INDEX
    Explanations

    character sequences

    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
    _plural
    -0.07
    å°ĺ
    -0.06
    ipop
    -0.06
    æĺ¯åģļ
    -0.06
    eu
    -0.06
    祺
    -0.06
    ahan
    -0.06
    fels
    -0.06
    occo
    -0.06
    -G
    -0.06
    POSITIVE LOGITS
    imore
    0.08
    _SIG
    0.08
    ateg
    0.08
     seme
    0.08
    oglob
    0.08
     поÑĩеÑĤ
    0.07
    unnable
    0.07
     اÙĦÙħÙĦ
    0.07
    zii
    0.07
    ä¸Ĭå¹´
    0.07
    Activations Density 0.013%

    No Known Activations