© 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. 39507
    Prev
    Next
    INDEX
    Explanations

    gene splicing variants

    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
    å¹³ä»ĵ
    -0.08
    解æĶ¾
    -0.07
    Unnamed
    -0.07
    tres
    -0.07
    rium
    -0.07
    imes
    -0.07
    奶
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
    _SYM
    -0.07
    lico
    -0.07
    POSITIVE LOGITS
     splice
    0.10
    ybrid
    0.08
     exon
    0.08
     transcripts
    0.08
    ç¼ĿåIJĪ
    0.08
    è£ģ
    0.08
    æĭ¼æİ¥
    0.08
    æ³£
    0.08
    åĪĩéĻ¤
    0.07
     transcript
    0.07
    Activations Density 0.025%

    No Known Activations