© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    detection of complications

    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
    áīµ
    -0.08
    hör
    -0.07
    зÑĭ
    -0.06
     Gale
    -0.06
    ceeded
    -0.06
    åĬłåĭĴ
    -0.06
    äºĨ解ä¸Ģä¸ĭ
    -0.06
    微信æī«ä¸Ģæī«
    -0.06
    ê·Ģ
    -0.06
    punt
    -0.06
    POSITIVE LOGITS
    's
    0.13
    åıĬåħ¶
    0.11
    ’s
    0.11
    \'
    0.09
    ´s
    0.09
    ‘s
    0.08
    imbang
    0.08
    arate
    0.08
    ().__
    0.08
    ä¹ĭæŃ»
    0.08
    Activations Density 0.576%

    No Known Activations