© 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. 47680
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
    lega
    -0.09
    (er
    -0.09
    åħ¶èĩªçĦ¶
    -0.08
    ussin
    -0.08
    nyder
    -0.08
    à¥įह
    -0.08
    sie
    -0.07
    IMUM
    -0.07
    cze
    -0.07
     pula
    -0.07
    POSITIVE LOGITS
    Ùĥر
    0.10
    gether
    0.08
    ë£Į
    0.08
     forth
    0.07
    ras
    0.07
    itto
    0.07
    ιαί
    0.07
    rap
    0.07
    ominated
    0.07
    סת
    0.07
    Activations Density 0.016%

    No Known Activations