© 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. 23343
    Prev
    Next
    INDEX
    Explanations

    or

    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
    .tagName
    -0.08
    è¦ģ强åĮĸ
    -0.08
    èĭij
    -0.08
    ÃģN
    -0.07
    ä¸įå¿ĺ
    -0.07
     zowel
    -0.07
    olim
    -0.07
    urate
    -0.07
    ä¸įè«ĸæĺ¯
    -0.07
    erais
    -0.07
    POSITIVE LOGITS
     else
    0.11
    _else
    0.10
    ä¸įçĦ¶
    0.08
     outright
    0.07
    åIJ¦åĪĻ
    0.07
    è¦ģä¸įçĦ¶
    0.07
    å¹²èĦĨ
    0.07
    èĩ³å°ij
    0.07
    æľīåħ¶ä»ĸ
    0.07
    else
    0.07
    Activations Density 0.054%

    No Known Activations