© 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. 14216
    Prev
    Next
    INDEX
    Explanations

    units with superscripts

    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
     co
    -0.07
    ros
    -0.06
    ier
    -0.06
    oret
    -0.06
    åĪ«
    -0.06
    çļİ
    -0.06
     sed
    -0.06
    emente
    -0.06
    irs
    -0.06
    atoio
    -0.06
    POSITIVE LOGITS
    åĭ¤åĭ¤æģ³æģ³
    0.08
    attes
    0.08
    oord
    0.08
    ä¸įåı¯æĢĿè®®
    0.08
    yant
    0.08
    iché
    0.08
    åħ¢åħ¢ä¸ļä¸ļ
    0.08
    _decorator
    0.07
    åĪĨ享åĨħ容
    0.07
     Temas
    0.07
    Activations Density 0.010%

    No Known Activations