© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48678
    Prev
    Next
    INDEX
    Explanations

    . followed by contrasting conjunctions

    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
    è¿Ļæĺ¯å¯¹
    -0.07
    æĮºçĽ´
    -0.07
    ริà¸Ļà¸Ĺรà¹Į
    -0.07
    éia
    -0.06
    å°±æĺ¯æĥ³
    -0.06
    å¥īè¡Į
    -0.06
     displayName
    -0.06
    ä¸įå¼ĥ
    -0.06
    ixed
    -0.06
    èijĽ
    -0.06
    POSITIVE LOGITS
    inama
    0.08
    缺ä¸Ģä¸įåı¯
    0.07
    anna
    0.07
    ụ
    0.07
    aranya
    0.07
    edel
    0.07
    luck
    0.07
    edin
    0.07
    iatr
    0.07
    á»ĭt
    0.07
    Activations Density 0.394%

    No Known Activations