© 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. 41121
    Prev
    Next
    INDEX
    Explanations

    algebraic expressions with multipliers

    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
     boost
    -0.07
    å½ĴåĬŁäºİ
    -0.07
    大年
    -0.07
    踢
    -0.07
    ä¸įçĶ¨æĭħå¿ĥ
    -0.07
    溢
    -0.07
     Corm
    -0.07
    è³ľ
    -0.07
    å¾ĹçĽĬäºİ
    -0.07
    boost
    -0.07
    POSITIVE LOGITS
     Worse
    0.10
     worse
    0.09
    omore
    0.07
    æĽ´æ²¡æľī
    0.07
    æ²īéĩįçļĦ
    0.07
    åĬłéĩį
    0.07
     :(
    0.07
    ¨
    0.07
    ä¸ĭåİ»äºĨ
    0.07
    akra
    0.07
    Activations Density 0.130%

    No Known Activations