© 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. 45327
    Prev
    Next
    INDEX
    Explanations

    pure, purely, pureness

    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
    ç²Ĺ
    -0.09
     marg
    -0.08
    ¬¸
    -0.07
    讹
    -0.07
     McCart
    -0.06
    ä½łåİ»
    -0.06
    å°Ĩå°±
    -0.06
    UDGE
    -0.06
    udge
    -0.06
     POD
    -0.06
    POSITIVE LOGITS
    纯粹çļĦ
    0.15
    纯粹
    0.14
     purely
    0.13
    åįķ纯çļĦ
    0.11
    åįķ纯
    0.11
    ç´Ķç²¹
    0.11
     pure
    0.11
    纯
    0.10
    ç´Ķ
    0.10
    ä¸į顾
    0.10
    Activations Density 0.079%

    No Known Activations