© 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. 34114
    Prev
    Next
    INDEX
    Explanations

    <string>

    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
    2
    -0.07
    3
    -0.07
    1
    -0.06
    utan
    -0.06
    èݲåŃIJ
    -0.06
    为
    -0.06
    esh
    -0.06
    5
    -0.06
     <
    -0.06
    All
    -0.05
    POSITIVE LOGITS
    ÄĽj
    0.11
    å¥Īä½ķ
    0.09
    chemes
    0.09
     забÑĥ
    0.08
    ä¼¼æĺ¯
    0.08
    ÙĥÙĬÙĦ
    0.08
    à¤ľà¥Ģ
    0.08
    ÑģÑĤÑĬ
    0.08
    ç»ĦæĪIJçļĦ
    0.08
    aczy
    0.08
    Activations Density 0.044%

    No Known Activations