© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42166
    Prev
    Next
    INDEX
    Explanations

    delegate

    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
    iness
    -0.09
    egy
    -0.08
    teenth
    -0.07
    деÑģÑıÑĤ
    -0.07
    ened
    -0.07
    поÑģледÑģÑĤвии
    -0.07
    obile
    -0.07
    ģ
    -0.07
    osoph
    -0.07
    aring
    -0.07
    POSITIVE LOGITS
    age
    0.08
    ä¸įæĺİçļĦ
    0.08
    гаÑĤ
    0.08
    estes
    0.08
    راÙĥ
    0.07
    ÄĽj
    0.07
    uela
    0.07
    ãĤıãĤĬ
    0.07
    好èĩªå·±çļĦ
    0.07
    ennent
    0.07
    Activations Density 0.083%

    No Known Activations