© 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. 26455
    Prev
    Next
    INDEX
    Explanations

    code blocks or special characters

    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
    æ²¥
    -0.07
    ipas
    -0.07
    使å®ĥ
    -0.07
    aranya
    -0.07
    /md
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
    ÑĢоÑı
    -0.06
    çĶļèĢħ
    -0.06
    éŀĭ帽
    -0.06
     priori
    -0.06
    POSITIVE LOGITS
    mil
    0.08
    æĪijä»¬çŁ¥éģĵ
    0.07
    ever
    0.07
    æĪIJçĨŁçļĦ
    0.07
    äºĭåĬ¡æīĢ
    0.07
    å½ĵä¸Ģ个
    0.07
    ãĥ¼ãĥĦ
    0.07
     подпи
    0.07
    erts
    0.06
    üst
    0.06
    Activations Density 0.008%

    No Known Activations