© 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. 12922
    Prev
    Next
    INDEX
    Explanations

    names and dates

    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
    à°¦
    -0.08
    Ú¯ÙĪÙĨ
    -0.08
    νομ
    -0.07
    erview
    -0.07
    Ascending
    -0.07
     неÑģÑĤандаÑĢÑĤ
    -0.07
    tage
    -0.07
     existent
    -0.07
    æ±ŁæµĻ
    -0.07
    çī¹èī²çļĦ
    -0.07
    POSITIVE LOGITS
    ks
    0.07
     Ram
    0.06
    ly
    0.06
    core
    0.06
    trip
    0.06
    oron
    0.06
    dain
    0.06
    lee
    0.06
    ----------------------------------------------------------------------
    0.06
    论æĸĩçļĦ
    0.06
    Activations Density 0.028%

    No Known Activations