© 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. 56906
    Prev
    Next
    INDEX
    Explanations

    other

    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
    ambang
    -0.07
    è·¨è¶Ĭ
    -0.07
    igli
    -0.07
    两ç§įæĸ¹å¼ı
    -0.07
    evel
    -0.07
    å±
    -0.07
    åĪģ
    -0.07
    èį¡
    -0.07
    æ£ī
    -0.07
    osate
    -0.07
    POSITIVE LOGITS
    çŃīåħ¶ä»ĸ
    0.15
    åħ¶ä»ĸ
    0.14
     other
    0.13
    åĪ«çļĦ
    0.13
    çļĦåħ¶ä»ĸ
    0.13
    à¸Ńืà¹Īà¸Ļ
    0.13
    åħ¶ä»ĸçļĦ
    0.12
    åħ¶å®ĥ
    0.12
     Other
    0.11
    other
    0.11
    Activations Density 0.268%

    No Known Activations