© 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. 50211
    Prev
    Next
    INDEX
    Explanations

    galleries, universities, and publications

    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
    adesh
    -0.08
    ä¼ļæīĢ
    -0.07
    nez
    -0.07
     Pial
    -0.07
    YPD
    -0.07
    eward
    -0.07
    maal
    -0.06
    spflicht
    -0.06
    nage
    -0.06
    çľ¼è§ģ
    -0.06
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.07
    lay
    0.07
     compliment
    0.07
    æİĴåIJį第ä¸Ģ
    0.07
    è´º
    0.07
    æµ·çĩķ
    0.07
    ennen
    0.06
    ort
    0.06
    è³Ģ
    0.06
    unist
    0.06
    Activations Density 0.493%

    No Known Activations