© 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. 2327
    Prev
    Next
    INDEX
    Explanations

    departure date or direction

    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
    nya
    -0.13
    çļĦ
    -0.10
    à¸Ħà¹Į
    -0.10
    оÑģÑĮ
    -0.10
    cape
    -0.10
    iggio
    -0.09
    çļĦãģ«ãĤĤ
    -0.09
    ivière
    -0.09
    abelle
    -0.09
    οÏħÏģγ
    -0.09
    POSITIVE LOGITS
    Ìģ
    0.08
    åī¯éĥ¨éķ¿
    0.07
    a
    0.07
     pháºŃn
    0.07
    cular
    0.07
     dozen
    0.07
    eb
    0.07
    T
    0.07
    ed
    0.07
    á»ĵn
    0.07
    Activations Density 0.003%

    No Known Activations