© 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. 14922
    Prev
    Next
    INDEX
    Explanations

    fragments, Vim, cocaine, pad, triangles, Terminal, fitness, Enchanting

    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
    jemu
    -0.07
    çªĺå¢ĥ
    -0.07
    ಲà³ģ
    -0.07
    ellis
    -0.07
     Teixe
    -0.07
    rs
    -0.07
    ä¸ŃèĦ±é¢ĸèĢĮåĩº
    -0.06
    _NEED
    -0.06
    ourke
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     itself
    0.07
    éĽĢ
    0.07
    æĥħæ·±
    0.06
    æĸ
    0.06
    é«ĺç§ij
    0.06
     Jah
    0.06
    æľ¬èº«
    0.06
    igner
    0.06
    ä¸īåħ«
    0.06
    gratis
    0.06
    Activations Density 0.040%

    No Known Activations