© 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. 42017
    Prev
    Next
    INDEX
    Explanations

    px, 0, power

    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
    à¤Łà¤ķ
    -0.09
    anch
    -0.08
    aruh
    -0.08
    ETTI
    -0.07
    bacher
    -0.07
    okok
    -0.07
    ড়া
    -0.07
    днÑı
    -0.07
    oley
    -0.07
    ajak
    -0.07
    POSITIVE LOGITS
    h
    0.07
    人æ°ijåħ±åĴĮåĽ½
    0.07
    $h
    0.06
    æģ¯
    0.06
    fit
    0.06
    代夫
    0.06
     mÆ°Æ¡i
    0.06
    ä¾
    0.06
    nos
    0.06
    hw
    0.06
    Activations Density 0.319%

    No Known Activations