© 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. 49322
    Prev
    Next
    INDEX
    Explanations

    dividers or mechanisms

    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
    chow
    -0.08
    δη
    -0.07
    èĩªéĩį
    -0.07
    Convertible
    -0.07
    ¨
    -0.07
    ä¸įæį¢
    -0.07
    HEMA
    -0.07
    ìĸ´ëĤĺ
    -0.07
    æĻ¦
    -0.07
    ä¸įå¦ĤæĦı
    -0.07
    POSITIVE LOGITS
    éĬŃ
    0.07
    åIJĮé¾Ħ
    0.07
    ÙħÙĦÙĩ
    0.07
    é¹½
    0.07
    çĽIJ
    0.07
    bies
    0.07
     Maio
    0.07
    å¡©
    0.07
     erected
    0.06
    åIJĮæĹ¶å¯¹
    0.06
    Activations Density 0.001%

    No Known Activations