© 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. 63700
    Prev
    Next
    INDEX
    Explanations

    practical application, use, and results

    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
    edly
    -0.10
    ekom
    -0.09
    jenigen
    -0.09
    eku
    -0.09
     Postar
    -0.09
    ÑĥÑĤ
    -0.09
    ertz
    -0.08
    olate
    -0.08
    edList
    -0.08
    ÑĥÑī
    -0.08
    POSITIVE LOGITS
    Ø©
    0.12
    ity
    0.12
    ness
    0.11
    issime
    0.09
    ÙĬØ©
    0.09
    zem
    0.08
    issimo
    0.08
    ation
    0.08
    ãģª
    0.08
    ities
    0.08
    Activations Density 0.013%

    No Known Activations