© 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. 4375
    Prev
    Next
    INDEX
    Explanations

    numbers and letters separated by punctuation

    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
    yste
    -0.08
    ossen
    -0.07
    NG
    -0.07
    大麻
    -0.07
    ake
    -0.07
    ãĥIJãĥ³
    -0.07
    osas
    -0.07
    orte
    -0.07
    çİīå±±
    -0.07
    ÄįÃŃ
    -0.07
    POSITIVE LOGITS
    æĽ´åĬłæĸ¹ä¾¿
    0.07
    åĩºåı£çļĦ
    0.06
    æĭĽèģĺç½ij
    0.06
    uars
    0.06
    hind
    0.06
    çĨĻ
    0.06
    attere
    0.06
    ivate
    0.06
    ä¹ĭçªĹ
    0.06
    alatan
    0.06
    Activations Density 0.716%

    No Known Activations