© 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. 18796
    Prev
    Next
    INDEX
    Explanations

    code definitions and structure

    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
    ä¸ĭåIJĮ
    -0.09
    ä¹Ĺ
    -0.08
    बà¤Ĥध
    -0.07
    cente
    -0.07
    ä¹ĭä¸į
    -0.07
    lassen
    -0.07
    áŀ¶áŁĨáŀĦ
    -0.07
    羣å®ŀæĢ§è´Łè´£
    -0.07
    åĽłç´łå½±åĵį
    -0.07
     pomp
    -0.07
    POSITIVE LOGITS
    åħ³äºİ
    0.07
    a
    0.07
    iev
    0.07
    ¹Ħ
    0.06
     Aad
    0.06
    ilk
    0.06
    ιαί
    0.06
    ulk
    0.06
    aro
    0.06
    ivate
    0.06
    Activations Density 0.002%

    No Known Activations