© 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. 16508
    Prev
    Next
    INDEX
    Explanations

    geometric, mathematical, or computational operations

    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
    ereum
    -0.09
    ouston
    -0.09
    udge
    -0.08
    ened
    -0.08
    ows
    -0.08
    غÙĩ
    -0.08
    isikan
    -0.08
    erring
    -0.08
    erner
    -0.08
    egers
    -0.07
    POSITIVE LOGITS
    als
    0.08
    uch
    0.08
    eel
    0.08
    好èĩªå·±çļĦ
    0.08
    ally
    0.08
     underway
    0.08
    sweise
    0.08
    ality
    0.08
    yssey
    0.07
    ially
    0.07
    Activations Density 0.054%

    No Known Activations