© 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. 12356
    Prev
    Next
    INDEX
    Explanations

    copyright disclaimer

    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
    çĥ§
    -0.07
    heb
    -0.07
    trace
    -0.06
    ä¼ļä»İ
    -0.06
    TRACE
    -0.06
    ç§į
    -0.06
    æĺ¯è¯´
    -0.06
    è¶Ł
    -0.06
    ä½įçļĦ
    -0.06
    ome
    -0.06
    POSITIVE LOGITS
    ucket
    0.07
    ialias
    0.07
    adero
    0.07
    wright
    0.07
    immä
    0.07
    shal
    0.07
    _cube
    0.07
    alt
    0.07
    nton
    0.07
    ιÏĥμÏĮ
    0.07
    Activations Density 0.006%

    No Known Activations