© 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. 40635
    Prev
    Next
    INDEX
    Explanations

    examples

    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
    åĶ¯ä¸Ģ
    -0.07
    åĶ¯ä¸ĢçļĦ
    -0.07
    è¿ĺæľīä¸Ģ个
    -0.07
    æľī两个
    -0.06
     slo
    -0.06
    ims
    -0.06
    åĶ¯ä¸Ģä¸Ģ个
    -0.06
    azzo
    -0.06
    æľīä¸ī个
    -0.06
    illen
    -0.06
    POSITIVE LOGITS
     examples
    0.14
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.13
    examples
    0.13
    Examples
    0.13
     Examples
    0.12
    åĪĹ举
    0.12
    常è§ģçļĦ
    0.11
    举ä¾ĭ
    0.11
    ispiele
    0.11
     exemplos
    0.10
    Activations Density 0.112%

    No Known Activations