© 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. 57853
    Prev
    Next
    INDEX
    Explanations

    device or agent suffixes

    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
     ná»ģn
    -0.07
    angani
    -0.07
    åıijå±ķ
    -0.07
    FileChooser
    -0.07
    åĪĽä¸ļçļĦ
    -0.07
    æĵ¦
    -0.07
    rauch
    -0.07
    æı©
    -0.07
    asih
    -0.07
    ãģļ
    -0.07
    POSITIVE LOGITS
    顾åIJįæĢĿä¹ī
    0.08
    ä¸įæĩĪ
    0.07
    å°±ä½į
    0.07
    yj
    0.06
    çŤ
    0.06
     tarafından
    0.06
    pector
    0.06
    çļĦä½ľçĶ¨ä¸ĭ
    0.06
    çļĦæķ°æį®æĺ¾ç¤º
    0.06
    ä¸į为
    0.06
    Activations Density 0.337%

    No Known Activations