© 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. 29877
    Prev
    Next
    INDEX
    Explanations

    steel archway

    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
    ixon
    -0.08
    abs
    -0.07
     absolutely
    -0.07
    chor
    -0.06
    ä¸ĢåĪĨ
    -0.06
    éĩįæķ´
    -0.06
    minster
    -0.06
    æĺ
    -0.06
    ãĥªãĥ¥ãĥ¼
    -0.06
    را
    -0.06
    POSITIVE LOGITS
    ãĢģãĢģ
    0.09
    erin
    0.08
    igné
    0.08
    DataFrame
    0.07
    uge
    0.07
    æľīæĪij
    0.07
    aris
    0.07
    .bs
    0.07
    eret
    0.07
    мок
    0.07
    Activations Density 0.218%

    No Known Activations