© 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. 13321
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

    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
    orney
    -0.07
     reform
    -0.07
     Reform
    -0.06
     Suc
    -0.06
    ëĭ¤ëĭĪ
    -0.06
    æİıåĩº
    -0.06
    éŃĶ女
    -0.06
    otta
    -0.06
    ICODE
    -0.06
    **(
    -0.06
    POSITIVE LOGITS
    +'.
    0.08
    ingin
    0.07
    ('').
    0.07
    ÙħÙĪÙĨ
    0.07
    ministr
    0.07
    çķĮ
    0.07
     fornit
    0.07
    æµİ
    0.07
    commended
    0.06
    lát
    0.06
    Activations Density 0.044%

    No Known Activations