© 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. 2768
    Prev
    Next
    INDEX
    Explanations

    programming context or code

    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
    most
    -0.06
    ,
    -0.06
     and
    -0.06
    å¯¹åľ¨
    -0.06
    æīĶåĪ°
    -0.06
    æł·
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.05
     Ehr
    -0.05
    3
    -0.05
    Ñħла
    -0.05
    POSITIVE LOGITS
     appunto
    0.10
    äºİè¡Į
    0.08
    asilan
    0.08
    ij¸
    0.08
    _strerror
    0.08
    åİ»ä½ķ
    0.08
    æīĢ欲è¨Ģ
    0.08
    波波
    0.08
    çĿĢå°ı
    0.08
    Qed
    0.08
    Activations Density 0.668%

    No Known Activations