© 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. 20667
    Prev
    Next
    INDEX
    Explanations

    RNA sequences and fragments

    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
    alie
    -0.08
    æ¼ıçĶµ
    -0.07
    aktu
    -0.07
    ç»ĻæĪijçķĻè¨Ģ
    -0.07
    pane
    -0.07
    éĶ¡
    -0.07
    çĽĪäºı
    -0.07
    .prevent
    -0.07
    åĨ¶
    -0.07
    æ³¢çļĦ
    -0.07
    POSITIVE LOGITS
     fragments
    0.09
     generated
    0.08
     fragment
    0.08
    ạc
    0.08
    æµĭåºı
    0.08
     lengths
    0.08
    Äĥr
    0.08
     tags
    0.07
    tags
    0.07
    ragments
    0.07
    Activations Density 0.011%

    No Known Activations