© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    Bible College, Hip Hop, J Play, leuk-osis, Hyacinths, Satellites, roofing sh, Shoe Repair

    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
    oda
    -0.07
    Ùĭ
    -0.07
    etlen
    -0.07
    оди
    -0.06
    usr
    -0.06
    ذاÙĥ
    -0.06
    opal
    -0.06
    ucht
    -0.06
    ìłķíķľ
    -0.06
    ologically
    -0.06
    POSITIVE LOGITS
    ฯ
    0.11
    çķĶ
    0.08
    <tool_response>
    0.08
    ipsoid
    0.08
    à¸Ļà¹Į
    0.07
    夫æĸ¯åŁº
    0.07
    æĻ®æ£®
    0.07
    à¸ģà¹Į
    0.07
    phony
    0.07
    çļ®ä¹¦
    0.07
    Activations Density 0.358%

    No Known Activations