© 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. 21920
    Prev
    Next
    INDEX
    Explanations

    united, order, opinion

    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
    Ùĩ
    -0.08
    ad
    -0.07
    大éĥ¨ä»½
    -0.07
    et
    -0.07
    b
    -0.07
    èĩªçĶ±èĩªåľ¨
    -0.07
    Ãĥ
    -0.07
    Æ°á»Ŀng
    -0.07
    å¼ķãģį
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    POSITIVE LOGITS
    ãģ¾ãģ¾
    0.08
    skyl
    0.07
    ãĥªãĥ¼ãĤº
    0.07
    essus
    0.07
    suming
    0.07
    edt
    0.07
    å§Ĺ
    0.07
    åı½
    0.07
    éĩij森
    0.07
    诵
    0.07
    Activations Density 0.043%

    No Known Activations