© 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. 64321
    Prev
    Next
    INDEX
    Explanations

    Thomas, Spain

    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
    otten
    -0.07
    -dir
    -0.07
    ake
    -0.06
    è¿ĺä¸į
    -0.06
    nitz
    -0.06
    ote
    -0.06
    :
    -0.06
    ï¼ļ
    -0.06
     |:
    -0.06
    大åı·
    -0.06
    POSITIVE LOGITS
    NECT
    0.08
    Unchecked
    0.08
    ä¸İå·¥ä½ľ
    0.08
    omÄĽ
    0.08
    HOST
    0.08
     меÑĤалли
    0.08
    åĽ²
    0.08
    æĥ³æĸ¹
    0.07
    .host
    0.07
    BUFF
    0.07
    Activations Density 0.016%

    No Known Activations