© 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. 1808
    Prev
    Next
    INDEX
    Explanations

    CSS properties and HTML attributes

    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
    ends
    -0.07
     sure
    -0.06
    度è¿ĩ
    -0.06
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.06
     Det
    -0.06
    lero
    -0.06
    Det
    -0.06
    _FLUSH
    -0.06
    å°º
    -0.06
    urre
    -0.06
    POSITIVE LOGITS
    EDIUM
    0.08
    ohnt
    0.08
    äºĮçŃī
    0.07
    водиÑĤелÑĮ
    0.07
    _tw
    0.07
    assar
    0.07
     пова
    0.07
    itest
    0.07
    TY
    0.07
    opal
    0.07
    Activations Density 0.134%

    No Known Activations