© 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. 7855
    Prev
    Next
    INDEX
    Explanations

    who can, who use, who contributed, who have, who are, who hope, who encourages

    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
    uous
    -0.09
    lah
    -0.09
    اÙĭ
    -0.09
    ively
    -0.08
    ally
    -0.08
    ÙĨب
    -0.08
    nya
    -0.08
    иÑİ
    -0.08
    mo
    -0.08
    ly
    -0.07
    POSITIVE LOGITS
    've
    0.11
    quiera
    0.10
    soever
    0.09
    ’ve
    0.09
    ÙĬÙĨ
    0.09
    à¥ĩ
    0.08
    oping
    0.08
     Äijặn
    0.08
    ÑģÑĤва
    0.08
    ptions
    0.07
    Activations Density 0.121%

    No Known Activations