© 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. 28798
    Prev
    Next
    INDEX
    Explanations

    current object/variable names

    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
    epen
    -0.08
    åįģ足
    -0.08
    ian
    -0.07
    elan
    -0.07
    ÅĻi
    -0.07
    ÅĻ
    -0.06
    æķ´ä½ĵçļĦ
    -0.06
    eln
    -0.06
    els
    -0.06
     tiên
    -0.06
    POSITIVE LOGITS
    apon
    0.08
    minos
    0.08
    财产ä¿ĿéĻ©èĤ¡ä»½æľīéĻIJåħ¬åı¸
    0.08
    anst
    0.07
    asaki
    0.07
    onne
    0.07
    ledge
    0.07
    Ùijد
    0.07
    umfang
    0.07
    åįĢçļĦ
    0.07
    Activations Density 0.017%

    No Known Activations