© 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. 24179
    Prev
    Next
    INDEX
    Explanations

    programming comments and 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
    å¸ľ
    -0.08
    Ïįν
    -0.08
     yı
    -0.07
    ä¼ļåıĺæĪIJ
    -0.07
     Whit
    -0.07
    PACK
    -0.07
    æĹ¥ä¸¾è¡Į
    -0.07
     pul
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    lh
    -0.07
    POSITIVE LOGITS
    å¿ĥæĢ¥
    0.07
    åĩij
    0.07
     succesfully
    0.07
     occured
    0.06
    çĥŁéħĴ
    0.06
    enso
    0.06
     paran
    0.06
    kens
    0.06
     rectific
    0.06
    ertz
    0.06
    Activations Density 0.005%

    No Known Activations