© 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. 20928
    Prev
    Next
    INDEX
    Explanations

    epididymal protease inhibitor

    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
    uzu
    -0.07
    V
    -0.06
    |
    -0.06
    -0.06
    vs
    -0.06
     N
    -0.06
     spare
    -0.06
     C
    -0.06
    1
    -0.06
    avers
    -0.06
    POSITIVE LOGITS
    rier
    0.09
     vegas
    0.09
    ritti
    0.09
    ByKey
    0.09
    iry
    0.08
    COMMAND
    0.08
    **–
    0.08
     à¹ģà¸ŀà¹ĩà¸Ħà¹Ģà¸ģà¸Ī
    0.08
    ÐłÐIJÐĿ
    0.08
    太éĥİ
    0.08
    Activations Density 0.342%

    No Known Activations