© 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. 30557
    Prev
    Next
    INDEX
    Explanations

    probability of picking sequence

    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
    äºĨä¸ĢäºĽ
    -0.08
    äºĨä¸Ģå®ļçļĦ
    -0.07
    yen
    -0.07
    lien
    -0.07
    rag
    -0.07
    äºĮè¦ģ
    -0.07
    äºĨäºĽ
    -0.07
    å¸ĮæľĽåı¯ä»¥
    -0.07
    éĢĤå½ĵ
    -0.06
    _allow
    -0.06
    POSITIVE LOGITS
    çļĦæ¦Ĥçİĩ
    0.09
     überhaupt
    0.09
     вообÑīе
    0.08
    æŁIJä¸Ģ
    0.08
     spontaneously
    0.08
     окажеÑĤÑģÑı
    0.08
     spontan
    0.08
    ÙĩÙī
    0.08
    æŁIJ个
    0.07
     randomly
    0.07
    Activations Density 0.044%

    No Known Activations