© 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. 45209
    Prev
    Next
    INDEX
    Explanations

    Lu and Lv contributed

    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
    amai
    -0.08
    à¸ŀล
    -0.08
    iben
    -0.08
    ipro
    -0.07
    roc
    -0.07
    ogi
    -0.07
    åĪ°æŶ
    -0.07
    mdl
    -0.07
    ,application
    -0.07
    phu
    -0.06
    POSITIVE LOGITS
    -Smith
    0.07
     forthcoming
    0.07
     et
    0.07
    abbr
    0.07
    rong
    0.07
    icket
    0.06
    èĶ·
    0.06
    zysz
    0.06
    IGHT
    0.06
    æĹ
    0.06
    Activations Density 0.002%

    No Known Activations