© 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. 63454
    Prev
    Next
    INDEX
    Explanations

    case study or report

    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
    ness
    -0.11
    ½Ķ
    -0.07
    ters
    -0.07
    çŃ
    -0.07
    ategory
    -0.07
    oku
    -0.07
    piler
    -0.07
    ennio
    -0.07
    ether
    -0.07
    ãĤ¹ãĤ¹ãĥ¡
    -0.06
    POSITIVE LOGITS
    æ¡Īä¾ĭ
    0.10
     case
    0.09
     cases
    0.09
    个æ¡Ī
    0.08
    trä
    0.08
    çļĦãģ«
    0.08
     Cases
    0.08
    zerű
    0.08
    çĻ¾æĪĺ
    0.07
    ÑĪÑĤе
    0.07
    Activations Density 0.054%

    No Known Activations