© 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. 41054
    Prev
    Next
    INDEX
    Explanations

    special characters like asterisks and quotes

    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
    å¥ĩèīº
    -0.07
    åĽ
    -0.07
    äºĨæķ´ä¸ª
    -0.07
    obb
    -0.06
    raid
    -0.06
    aur
    -0.06
    人以
    -0.06
    Ãļ
    -0.06
    гаÑĢ
    -0.06
    uru
    -0.06
    POSITIVE LOGITS
    retien
    0.08
    otec
    0.08
    ainen
    0.07
    apai
    0.07
    ffici
    0.07
    klen
    0.07
    kut
    0.07
    angan
    0.07
    lje
    0.07
    oves
    0.07
    Activations Density 0.157%

    No Known Activations