© 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. 23087
    Prev
    Next
    INDEX
    Explanations

    list starters

    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
     @}
    -0.08
    ç¬
    -0.07
    loat
    -0.07
    xe
    -0.07
    kee
    -0.07
    æľīæĺİæĺ¾
    -0.07
    人éĹ´
    -0.07
    หมาย
    -0.07
    #endregion
    -0.06
    ftar
    -0.06
    POSITIVE LOGITS
    ì¡°íļĮ
    0.09
    åıijå¸ĥæŶéĹ´
    0.07
    ä½ľèĢħ
    0.07
    éĺħ读éĩı
    0.07
    æµģ浪
    0.06
    æĪijä¹Łè¦ģ
    0.06
    åŃĹæķ°
    0.06
    æĹ¥æľŁ
    0.06
    jom
    0.06
    abt
    0.06
    Activations Density 1.519%

    No Known Activations