© 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. 47594
    Prev
    Next
    INDEX
    Explanations

    Track purpose, ultralight, Ruger LCP, nonprofits seek

    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
    idth
    -0.08
    ÏĦÏģοÏĨ
    -0.07
    راØŃ
    -0.07
    æĪļ
    -0.07
    bero
    -0.07
    æ±IJ
    -0.07
     chôm
    -0.07
    estig
    -0.07
    :index
    -0.07
    ίκ
    -0.07
    POSITIVE LOGITS
    ì°©
    0.07
    baden
    0.07
    xie
    0.07
    大åħ¨
    0.07
    ãĤĴçĻº
    0.06
    üss
    0.06
    arden
    0.06
    ضØŃ
    0.06
    jni
    0.06
     dint
    0.06
    Activations Density 0.003%

    No Known Activations