© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14563
    Prev
    Next
    INDEX
    Explanations

    special characters 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
    enberg
    -0.08
    -0.07
    Æ°Æ¡ng
    -0.07
    erals
    -0.07
    eral
    -0.07
    elen
    -0.07
    versa
    -0.06
    rate
    -0.06
    acter
    -0.06
    Ø©
    -0.06
    POSITIVE LOGITS
    utto
    0.09
    æĦıçļĦ
    0.08
    zelfde
    0.08
    pris
    0.08
    °
    0.08
    ujur
    0.08
    ÄįÃŃ
    0.08
    tring
    0.07
    ä¸Ģæĺ¯
    0.07
    kev
    0.07
    Activations Density 0.002%

    No Known Activations