© 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. 30280
    Prev
    Next
    INDEX
    Explanations

    foreign language titles and descriptions

    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
    opat
    -0.07
    继ç»ŃåĬªåĬĽ
    -0.07
    YW
    -0.07
     |/
    -0.07
    请ä¸ĭè½½
    -0.07
    nem
    -0.07
    æİı
    -0.07
    çĪ¬åĪ°
    -0.07
    estina
    -0.07
    **|
    -0.07
    POSITIVE LOGITS
    çļĦæĦıæĢĿ
    0.09
    ãģ¨ãģĦãģĨæĦıåij³
    0.08
    ä¹ĭæĦı
    0.07
    /
    0.07
    ahlen
    0.07
    urgi
    0.06
    haps
    0.06
    0.06
    罩
    0.06
     demek
    0.06
    Activations Density 0.063%

    No Known Activations