© 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. 8554
    Prev
    Next
    INDEX
    Explanations

    letters picked from

    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
    urator
    -0.11
    ä¸įäºĨçļĦ
    -0.08
    ä¸įäºĨ
    -0.08
    elt
    -0.08
    ron
    -0.08
    âĶģâĶģâĶģâĶģâĶģâĶģâĶģâĶģ
    -0.08
    ergestellt
    -0.07
     ÐĶополни
    -0.07
    ordial
    -0.07
    ertools
    -0.07
    POSITIVE LOGITS
    almente
    0.11
    halb
    0.09
    ized
    0.08
     اÙĦØŃÙĬÙĪÙĬØ©
    0.08
    ize
    0.08
    reopen
    0.08
    abyrin
    0.08
    ington
    0.08
    asing
    0.08
    æł·çļĦ
    0.07
    Activations Density 0.023%

    No Known Activations