© 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. 21367
    Prev
    Next
    INDEX
    Explanations

    is following by common question words

    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
    迹
    -0.08
    çļ®çĤİ
    -0.08
    象
    -0.08
    irates
    -0.08
    usic
    -0.07
    çģ«çº¿
    -0.07
    aries
    -0.07
    å¹²åĴ³
    -0.07
    æľīéĻIJ责任
    -0.07
    yal
    -0.07
    POSITIVE LOGITS
    nock
    0.09
    循åºı
    0.07
    ICE
    0.06
    çĶ¨ä»¥
    0.06
    ↵
    0.06
    ¬
    0.06
    ิà¹īà¸ĩ
    0.06
    ↵↵
    0.06
    cj
    0.06
    ÑĢÑı
    0.06
    Activations Density 0.048%

    No Known Activations