© 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. 18486
    Prev
    Next
    INDEX
    Explanations

    correct 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
    heel
    -0.08
    wein
    -0.08
    æĤį
    -0.07
    éĥ½æĺ¯åĽłä¸º
    -0.07
    éĥ½æĺ¯éĿŀ常
    -0.07
    edly
    -0.07
    xit
    -0.07
    iché
    -0.07
     ÐĴообÑīе
    -0.07
     Called
    -0.06
    POSITIVE LOGITS
     tast
    0.08
    ieri
    0.08
    并举
    0.07
    享åıĹ
    0.07
     unless
    0.06
     ÑģÑĤоÑĢон
    0.06
    uchs
    0.06
    inders
    0.06
    æĬµ
    0.06
    Handlers
    0.06
    Activations Density 0.007%

    No Known Activations