© 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. 34021
    Prev
    Next
    INDEX
    Explanations

    Warranty, status, deal, Iraq, nun, location

    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
    alay
    -0.08
    ï¸ı
    -0.08
    天ä¸ĭ
    -0.08
    <|box_end|>
    -0.07
    iores
    -0.07
    ska
    -0.07
    ól
    -0.07
    yor
    -0.07
    à¸ĺาà¸Ļี
    -0.07
    cion
    -0.06
    POSITIVE LOGITS
    äºİ
    0.07
    itti
    0.07
    ope
    0.07
    диод
    0.07
    derland
    0.06
    icha
    0.06
    ä¸ĢéĹª
    0.06
    æĹłæĢ¨
    0.06
     hete
    0.06
    udd
    0.06
    Activations Density 0.569%

    No Known Activations