© 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. 25013
    Prev
    Next
    INDEX
    Explanations

    ex rel

    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
    èĥİ
    -0.07
    æł¼å±Ģ
    -0.07
    ¨
    -0.06
     gains
    -0.06
    ç¨Ģ
    -0.06
    assar
    -0.06
    çĽ¸çº¦
    -0.06
    olume
    -0.06
    æŃ»äºº
    -0.06
    ÑģÑı
    -0.06
    POSITIVE LOGITS
     onto
    0.09
    urga
    0.08
    çĸĻ
    0.08
     perpendicular
    0.07
    åŀĤ缴
    0.07
    راØŃ
    0.07
    禮
    0.07
    wohl
    0.07
    çĶ¨æĪ·å¯¹
    0.07
    Iso
    0.07
    Activations Density 0.003%

    No Known Activations