© 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. 16710
    Prev
    Next
    INDEX
    Explanations

    problem statements

    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
     localtime
    -0.09
    ãĤŃãĥ¥ãĥ¼
    -0.08
     Gep
    -0.07
    arkin
    -0.07
    åĨ¤æŀī
    -0.07
    po
    -0.07
    éĩĮäºļ
    -0.07
    åѤåĦ¿
    -0.07
    .overflow
    -0.07
    dcc
    -0.06
    POSITIVE LOGITS
    luss
    0.07
     concentrate
    0.07
    vier
    0.07
    åIJĪåIJĮ约å®ļçļĦ
    0.07
    ä¸įçĶļ
    0.07
     Michaels
    0.07
     iepazÄ«Å¡anÄģs
    0.07
     #=>
    0.06
     spiagg
    0.06
    ä½įåŃIJ
    0.06
    Activations Density 0.008%

    No Known Activations