© 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. 38567
    Prev
    Next
    INDEX
    Explanations

    unfold and deploy

    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
    innacle
    -0.09
    aceous
    -0.08
    าà¸Ļุ
    -0.08
    åıijèªĵ
    -0.08
    atti
    -0.08
    eland
    -0.08
    дика
    -0.08
    tdown
    -0.08
    irk
    -0.08
    wai
    -0.08
    POSITIVE LOGITS
    ings
    0.08
    nable
    0.08
    ed
    0.08
    ä¸ŃåĽ½å®¶
    0.08
     Äijặn
    0.07
    à¸ģวà¹īาà¸ĩ
    0.07
    ément
    0.07
    a
    0.07
    اظ
    0.07
    ness
    0.07
    Activations Density 0.015%

    No Known Activations