© 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. 33392
    Prev
    Next
    INDEX
    Explanations

    special characters like č

    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
    er
    -0.13
    rw
    -0.09
    ieme
    -0.08
    à§įড
    -0.08
    naires
    -0.08
    oes
    -0.08
    ÙĬاء
    -0.08
    rata
    -0.08
    ISTRA
    -0.08
    à§įত
    -0.08
    POSITIVE LOGITS
    essional
    0.10
    à¸ģรรม
    0.08
    oenix
    0.07
    ondi
    0.07
    GRAM
    0.07
    eding
    0.07
    ourcen
    0.07
    ãģī
    0.07
    ìį¨
    0.07
    Äĥmânt
    0.07
    Activations Density 0.011%

    No Known Activations