© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2496
    Prev
    Next
    INDEX
    Explanations

    i to

    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
    anine
    -0.08
    eah
    -0.08
    æĪijæĿ¥è¯´ä¸¤åı¥
    -0.08
    pekt
    -0.08
    -single
    -0.08
    åįķéĹ´
    -0.07
    ossi
    -0.07
    åįķ身
    -0.07
    ä¾
    -0.07
    uddy
    -0.07
    POSITIVE LOGITS
    yel
    0.07
    æł¹æį®
    0.07
    å§Ķæīĺ
    0.07
    มุ
    0.07
    isc
    0.07
    undes
    0.06
    ä¼ij
    0.06
    æĶ¯
    0.06
    lem
    0.06
    кÑĥÑĢа
    0.06
    Activations Density 0.024%

    No Known Activations