© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15054
    Prev
    Next
    INDEX
    Explanations

    Los Angeles to

    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
    '&&
    -0.08
    ://"
    -0.08
    ä¸İå·¥ä½ľ
    -0.07
    æ±Łåİ¿
    -0.07
     Pruitt
    -0.07
    *&
    -0.07
    å¥
    -0.07
    ://'
    -0.07
    大ä¸Ģ
    -0.07
     bowiem
    -0.07
    POSITIVE LOGITS
    åĨįåĬł
    0.08
    ãģĿãģĹãģ¦
    0.08
    åĨįåĬłä¸Ĭ
    0.07
    åĨįåĪ°
    0.07
    seealso
    0.07
    è¿ĺæľīä¸Ģ个
    0.07
    oad
    0.07
     etc
    0.07
    è¿ĺæľīä¸Ģç§į
    0.07
    ฯ
    0.07
    Activations Density 0.057%

    No Known Activations