© 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. 65115
    Prev
    Next
    INDEX
    Explanations

    Mert, Jo, Square, main

    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
    ensively
    -0.06
    ç»Ħç»ĩå¼Ģå±ķäºĨ
    -0.06
     gam
    -0.06
    egah
    -0.06
    PILE
    -0.06
     insomma
    -0.06
    ulary
    -0.06
    بÙĪد
    -0.06
    isst
    -0.06
    ä¸Ĭ好
    -0.06
    POSITIVE LOGITS
    ãģĶ
    0.08
     Horiz
    0.07
     esque
    0.07
    undra
    0.07
    iri
    0.07
    наÑĤ
    0.07
    è¯Ńè¨ĢåĴĮ
    0.07
    禺
    0.07
    çѱ
    0.07
    ä¸ĵ
    0.06
    Activations Density 0.003%

    No Known Activations