© 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. 29075
    Prev
    Next
    INDEX
    Explanations

    patterns in research protocols or studies

    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
    ume
    -0.07
    [
    -0.06
    iture
    -0.06
    umped
    -0.06
    gregated
    -0.06
    尿裤
    -0.06
    éĥİ
    -0.06
    zer
    -0.06
    iot
    -0.05
     fame
    -0.05
    POSITIVE LOGITS
    æĹłè®ºæĺ¯
    0.09
     nho
    0.09
    _UNDEF
    0.08
    igrams
    0.08
    ifest
    0.08
    æłĩåĩĨ为
    0.08
    еÑĢÑĭ
    0.07
    åį
    0.07
    .NewRequest
    0.07
    èį·
    0.07
    Activations Density 0.101%

    No Known Activations