© 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. 10856
    Prev
    Next
    INDEX
    Explanations

    text after 'i'

    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
    .relative
    -0.07
    ive
    -0.06
    çĶ
    -0.06
    usher
    -0.06
    åħ¬
    -0.06
    ä»»åĬ³ä»»æĢ¨
    -0.06
     opro
    -0.06
    aland
    -0.06
    å¸Ń
    -0.06
     unknown
    -0.06
    POSITIVE LOGITS
     ÑıкобÑĭ
    0.09
    ละ
    0.08
    稼
    0.07
    è¿ĺæĺ¯ä¼ļ
    0.07
    ä¸įåºĶ该
    0.07
    ç±»æ¯Ķ
    0.07
    è¿ĺæĺ¯åı¯ä»¥
    0.07
    æĺ¯åIJ¦ä¼ļ
    0.07
    æĦŁè§ī
    0.07
    _should
    0.07
    Activations Density 0.079%

    No Known Activations