© 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. 24470
    Prev
    Next
    INDEX
    Explanations

    attached to or located in

    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
    ownt
    -0.07
    æĽ´å¤ļåĨħ容
    -0.07
    ignan
    -0.07
     ourselves
    -0.07
    asis
    -0.07
    ier
    -0.07
    ombat
    -0.07
    asian
    -0.07
    cev
    -0.07
    elight
    -0.07
    POSITIVE LOGITS
    åħ¶åIJİ
    0.07
     alongside
    0.07
    çĶ¨æĿ¥
    0.07
    à¸Ĺà¹īาย
    0.07
     коÑĤоÑĢой
    0.06
    æĺ¾çľ¼
    0.06
     коÑĤоÑĢÑĭми
    0.06
    جÙĪ
    0.06
    uten
    0.06
     beforehand
    0.06
    Activations Density 0.610%

    No Known Activations