© 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. 11819
    Prev
    Next
    INDEX
    Explanations

    "Full Name:"

    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
    vaard
    -0.08
    éĽ¨éľ²
    -0.08
    (ignore
    -0.07
    {name
    -0.07
     Woods
    -0.07
    quio
    -0.07
    pl
    -0.06
    letz
    -0.06
    ä»¥ä¾Ľ
    -0.06
    chwitz
    -0.06
    POSITIVE LOGITS
    arth
    0.08
    rush
    0.07
    erso
    0.07
    åĬĽä½ľ
    0.07
    oday
    0.06
    atnya
    0.06
    éĻIJãĤĬ
    0.06
    èĩªçĦ¶ä¸įä¼ļ
    0.06
    å§Ĩ
    0.06
    .theme
    0.06
    Activations Density 0.010%

    No Known Activations