© 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. 7774
    Prev
    Next
    INDEX
    Explanations

    disc, costs, booth, port, IP, jury

    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
    idente
    -0.07
     vigil
    -0.07
    微信æī«ä¸Ģæī«
    -0.06
     dại
    -0.06
     Sid
    -0.06
     Hutchinson
    -0.06
    æī¿æĭħä¸ĢåĪĩ
    -0.06
    iglio
    -0.06
    SID
    -0.06
    没æľīæĥ³åĪ°
    -0.06
    POSITIVE LOGITS
    æĪĸ缴æİ¥
    0.13
    æĪĸ以
    0.12
    Mode
    0.11
    æĪĸéĢļè¿ĩ
    0.11
    æĪĸèĢħ缴æİ¥
    0.11
    -mode
    0.11
    æĪĸçĶ¨
    0.11
     mode
    0.11
    å¼ı
    0.10
    mode
    0.10
    Activations Density 0.335%

    No Known Activations