© 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. 40882
    Prev
    Next
    INDEX
    Explanations

    slot machine

    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
    å·²çŁ¥
    -0.07
    æĴ®
    -0.06
    rones
    -0.06
    ä¹Łè·Ł
    -0.06
    ãģ¡
    -0.06
    å¯Ĩä¸įåı¯
    -0.06
    è¦ģåħĪ
    -0.06
    游åŃIJ
    -0.06
    çŁ¥åIJįçļĦ
    -0.06
    ä¿ĥè¿ĽåѦçĶŁ
    -0.06
    POSITIVE LOGITS
    ultat
    0.08
    iete
    0.08
    ult
    0.08
     иÑģко
    0.07
    ejo
    0.07
    colas
    0.07
     proves
    0.07
    çĤ¹åĩ»ä¸ĭè½½
    0.07
    rados
    0.07
    符åIJĪè¦ģæ±Ĥ
    0.07
    Activations Density 0.005%

    No Known Activations