© 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. 31287
    Prev
    Next
    INDEX
    Explanations

    adapt/adaptation

    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
    theless
    -0.08
    Äija
    -0.08
    Handled
    -0.08
    mehr
    -0.07
    zelf
    -0.07
    ielo
    -0.07
     aparte
    -0.07
    zeuge
    -0.07
    hound
    -0.07
    iley
    -0.07
    POSITIVE LOGITS
    ively
    0.11
    elaide
    0.11
    æĢ§å¼º
    0.10
    /ad
    0.10
    ocaly
    0.09
    æĢ§çļĦ
    0.08
    ÑĤаÑĨиÑı
    0.08
    ä¸įäºĨçļĦ
    0.08
    æĢ§åľ°
    0.08
    è¿ĩæĿ¥çļĦ
    0.08
    Activations Density 0.044%

    No Known Activations