© 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. 42131
    Prev
    Next
    INDEX
    Explanations

    central, center, Z(G)

    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
    _urls
    -0.08
    DER
    -0.07
    æį¢
    -0.07
    ONSE
    -0.07
     rej
    -0.07
    æį¢ä¸Ģ个
    -0.07
    çľ¼çľ¶
    -0.07
    .urls
    -0.07
    urls
    -0.07
    æĢ»ç»ĵç»ıéªĮ
    -0.07
    POSITIVE LOGITS
    .singleton
    0.07
    åħ¨ä½ĵ
    0.07
    å¡ļ
    0.07
    OfFile
    0.06
    ìŀī
    0.06
    áĥĸ
    0.06
    singleton
    0.06
    çĭ±
    0.06
    er
    0.06
    ç¼Ńç»ķ
    0.06
    Activations Density 0.005%

    No Known Activations