© 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. 51532
    Prev
    Next
    INDEX
    Explanations

    References and titles

    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
    lauf
    -0.08
    裳
    -0.08
    ujan
    -0.08
    uha
    -0.08
    tml
    -0.08
    UNT
    -0.07
    ellini
    -0.07
    浪
    -0.07
    ima
    -0.07
    ÙĦÙĥ
    -0.07
    POSITIVE LOGITS
    å°ı贴士
    0.08
     nata
    0.07
     amb
    0.06
    æĢ»ä½ĵèĢĮè¨Ģ
    0.06
    å¸IJåı·
    0.06
    ิà¹īà¸ĩ
    0.06
    _rights
    0.06
    lifetime
    0.06
    çļĦæŶåĢĻä¼ļ
    0.06
    æĬ¥äºĨ
    0.06
    Activations Density 0.281%

    No Known Activations