© 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. 64369
    Prev
    Next
    INDEX
    Explanations

    HTML entities and special characters

    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
    baugh
    -0.11
    meÄiju
    -0.09
    иÑİ
    -0.09
    bourne
    -0.09
    yla
    -0.09
    اÙĨØ´
    -0.08
    ä¸įçĦ¶
    -0.08
    lander
    -0.08
    onat
    -0.08
    borne
    -0.08
    POSITIVE LOGITS
    nbsp
    0.15
    jenigen
    0.09
    quot
    0.09
    ï¸ı
    0.09
    emsp
    0.09
    sWith
    0.08
    ลฯ
    0.08
    пли
    0.08
    amental
    0.08
    amp
    0.08
    Activations Density 0.092%

    No Known Activations