© 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. 21480
    Prev
    Next
    INDEX
    Explanations

    default settings or options

    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
    quier
    -0.09
    ä½łçļĦæīĭæľº
    -0.07
    åģİ
    -0.07
    çļĦèĮĥåĽ´
    -0.07
    åIJįåī¯
    -0.07
     Laurea
    -0.07
     scram
    -0.07
    اØŃØ©
    -0.07
     Sido
    -0.07
    éĢīä¸Ģ
    -0.07
    POSITIVE LOGITS
    /default
    0.08
    DEFAULT
    0.08
    æĺ¯åĶ¯ä¸Ģ
    0.08
    è·¯å¾Ħ
    0.08
    èIJ½
    0.08
     DEFAULT
    0.07
    åºıåĪĹ
    0.07
    é»ĺ认
    0.07
     baseline
    0.07
     default
    0.07
    Activations Density 0.065%

    No Known Activations