© 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. 27943
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    ¹Ħ
    -0.07
    orsi
    -0.07
    ζη
    -0.07
    otti
    -0.06
    dal
    -0.06
    dre
    -0.06
    å¤įçĶ¨
    -0.06
    à¹Ĥ
    -0.06
    boli
    -0.06
     Luckily
    -0.06
    POSITIVE LOGITS
    estiv
    0.07
    inando
    0.07
    ÛĮتÛĮ
    0.07
    <|fim_prefix|>
    0.07
     молоÑĩной
    0.07
    umped
    0.07
     scrimmage
    0.07
    COPE
    0.07
    ModelState
    0.07
    ä¹ĭæĹ¥æŃ¢
    0.07
    Activations Density 0.018%

    No Known Activations