© 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. 61791
    Prev
    Next
    INDEX
    Explanations

    UI development terms

    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
    åŃIJéĩĮ
    -0.07
    ously
    -0.07
    -eyed
    -0.07
    æĢ§åĬŁèĥ½
    -0.07
    ddie
    -0.07
    á»ī
    -0.07
    odzi
    -0.07
    使çĶ¨è¿ĩç¨ĭä¸Ń
    -0.07
    optic
    -0.07
    _handlers
    -0.07
    POSITIVE LOGITS
    ers
    0.09
    çļĦ
    0.08
    teen
    0.08
    åĽĽä¸ªåŃĹ
    0.07
    ocat
    0.07
    wich
    0.07
    èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.07
    lege
    0.07
    ìĿĺ
    0.07
    entifier
    0.07
    Activations Density 0.051%

    No Known Activations