© 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. 44919
    Prev
    Next
    INDEX
    Explanations

    known characteristics or properties

    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
    APH
    -0.08
    asilan
    -0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    -0.07
    ést
    -0.07
    undai
    -0.07
    ánÃŃ
    -0.07
    æĺłåħ¥
    -0.07
    ãĤĬãģĻãĤĭ
    -0.07
    Prime
    -0.07
    £¼
    -0.07
    POSITIVE LOGITS
     known
    0.19
    known
    0.17
     predictable
    0.17
    å·²çŁ¥
    0.17
    Known
    0.16
     Known
    0.15
    çŁ¥éģĵ
    0.14
     knowing
    0.14
    _known
    0.13
     know
    0.13
    Activations Density 0.169%

    No Known Activations