© 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. 45526
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or specific nouns

    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
    éŁ
    -0.06
    ëŀĺ
    -0.06
     sewaktu
    -0.06
    强çļĦ
    -0.06
    este
    -0.06
    éģIJ
    -0.06
    GLE
    -0.06
    ä¸Ĭè¿°
    -0.06
    åĴĮåĪĺ
    -0.06
    åįļä¼ļ
    -0.06
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.08
    öt
    0.07
    igel
    0.07
    edale
    0.07
    _SHIFT
    0.07
    æį¶
    0.07
    furt
    0.07
    oup
    0.07
    åħ¶æ¬¡
    0.07
    igit
    0.07
    Activations Density 0.984%

    No Known Activations