© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11012
    Prev
    Next
    INDEX
    Explanations

    internet marketing, dating, repair

    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
    Âł
    -0.08
    ÃįT
    -0.08
    -0.07
    à¦¾à¦ľ
    -0.07
    ostr
    -0.07
    ucch
    -0.07
    inter
    -0.07
    åĬ±
    -0.06
     enf
    -0.06
     INFORMAZ
    -0.06
    POSITIVE LOGITS
    ä¸ĺ
    0.07
    edul
    0.07
    emez
    0.07
    .instant
    0.07
    0.07
    空
    0.07
    ç§Ģ
    0.07
    itian
    0.07
    .yahoo
    0.07
    æ´ŀ
    0.07
    Activations Density 0.294%

    No Known Activations