© 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. 64814
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions or non-latin 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
    èĭ¥ä¸įæĺ¯
    -0.06
    ele
    -0.06
    å°ı红
    -0.06
    å°½æľī
    -0.06
     Zad
    -0.06
     Gathering
    -0.06
    omb
    -0.06
     Bers
    -0.06
    ÃŃp
    -0.06
    åIJĦ
    -0.06
    POSITIVE LOGITS
    åľ¨æŃ¤åŁºç¡Ģä¸Ĭ
    0.11
     thereafter
    0.10
     afterwards
    0.10
     ÙĦاØŃÙĤ
    0.09
     afterward
    0.09
    è¿Ļæīįæĺ¯
    0.08
    åIJİç»ŃçļĦ
    0.08
    ereum
    0.08
    éļıåIJİ
    0.08
    ØŃÙĬÙĨ
    0.08
    Activations Density 0.027%

    No Known Activations