© 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. 13879
    Prev
    Next
    INDEX
    Explanations

    comment markers or special characters

    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
    ãĤ£
    -0.07
     há»ĵn
    -0.07
    abcdefghijkl
    -0.07
    ivec
    -0.07
    arre
    -0.07
    .require
    -0.07
    emberg
    -0.07
    nad
    -0.07
    uela
    -0.07
    åĬłæĶ¶
    -0.07
    POSITIVE LOGITS
    çĵ¢
    0.08
    BUG
    0.07
    ำà¸Ļ
    0.07
    аÑģÑĤ
    0.07
    é«ĺè°ĥ
    0.06
    æĥ³åĪ°è¿ĻéĩĮ
    0.06
    度
    0.06
    iski
    0.06
    asty
    0.06
    ÑĤони
    0.06
    Activations Density 0.072%

    No Known Activations