© 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. 2133
    Prev
    Next
    INDEX
    Explanations

    item(s)

    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
    çķ¥
    -0.08
    åĴĮèĩªå·±çļĦ
    -0.08
    aille
    -0.07
    uing
    -0.07
    ÑĨÑĮ
    -0.07
    idar
    -0.07
    vlo
    -0.07
    usy
    -0.07
    usak
    -0.07
    éĢĤåIJĪèĩªå·±çļĦ
    -0.07
    POSITIVE LOGITS
    0.08
    æŁIJç§į
    0.08
    å¼Ģåı£éģĵ
    0.07
    æŁIJ个
    0.07
    Âł
    0.06
    æĬĬä¸Ģ个
    0.06
    ards
    0.06
    âĢ
    0.06
    âĢĮ
    0.06
     d
    0.06
    Activations Density 0.016%

    No Known Activations