© 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. 27246
    Prev
    Next
    INDEX
    Explanations

    numbers and 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
    ä¼ĹæīĢåij¨çŁ¥
    -0.08
    åĬłæĭ¿å¤§
    -0.07
    ä¸įå°±
    -0.06
    igd
    -0.06
    ffects
    -0.06
    dex
    -0.06
    ig
    -0.06
    éĽĦ
    -0.06
     allá
    -0.06
    fique
    -0.06
    POSITIVE LOGITS
    anager
    0.08
    åĪĩå®ŀåģļ好
    0.08
    uches
    0.08
    áĢĬáĢºáĢ¸
    0.08
    æķ´æĶ¹èIJ½å®ŀ
    0.07
     Pellegr
    0.07
    æķ¬çĪ±çļĦ
    0.07
    ÙıÙĪÙĦ
    0.07
    FromFile
    0.07
    iscal
    0.07
    Activations Density 0.015%

    No Known Activations