© 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. 61720
    Prev
    Next
    INDEX
    Explanations

    explains or defines

    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
    å°Ĩå®ĥ
    -0.08
    æĬĬå®ĥ
    -0.08
    使å®ĥ
    -0.08
    regar
    -0.08
    è°Ī
    -0.08
    anas
    -0.07
    etÃŃ
    -0.07
    yant
    -0.07
    undler
    -0.07
    IRCLE
    -0.07
    POSITIVE LOGITS
    емо
    0.07
    ãģĿãĤį
    0.06
    arth
    0.06
     contribute
    0.06
    åŁŁçļĦ
    0.06
     ÑģвеÑĤоди
    0.06
    rem
    0.06
    微信æī«ä¸Ģæī«
    0.06
    æľ¬ç«Ļ
    0.06
    è´¡çĮ®
    0.06
    Activations Density 0.019%

    No Known Activations