© 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. 56158
    Prev
    Next
    INDEX
    Explanations

    several followed by a noun

    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
    ters
    -0.08
    ä¸Ŀ毫
    -0.08
    ixe
    -0.08
    icle
    -0.08
     semula
    -0.08
    <|box_end|>
    -0.08
    uts
    -0.08
    yon
    -0.08
    ukai
    -0.08
    Ú©ÙĦ
    -0.07
    POSITIVE LOGITS
     dozen
    0.12
     hundred
    0.10
    iating
    0.08
    -sided
    0.08
    ê°Ģì§Ģ
    0.08
     thousand
    0.08
    fois
    0.08
    Ùĩ
    0.08
    ed
    0.07
    /se
    0.07
    Activations Density 0.150%

    No Known Activations