© 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. 40591
    Prev
    Next
    INDEX
    Explanations

    specific conditions for success

    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
    为æİ¨è¿Ľ
    -0.09
    reif
    -0.08
    adel
    -0.08
    apura
    -0.08
    obili
    -0.08
    hofer
    -0.08
     أص
    -0.08
    è¿Ļå°±è¦ģæ±Ĥ
    -0.08
    为æݨåĬ¨
    -0.08
    eltas
    -0.08
    POSITIVE LOGITS
    ä¸įä»ħèĥ½
    0.10
    å°Ĩ使
    0.10
    æīįèĥ½ä¿Ŀè¯ģ
    0.10
    åı¯ä»¥ä¿Ŀè¯ģ
    0.09
     ensures
    0.09
    à¸Īะà¸Ĺำà¹ĥหà¹ī
    0.09
    æĹ¢èĥ½
    0.09
    æīįèĥ½ä½¿
    0.09
    è¿Ļæł·åı¯ä»¥
    0.09
    åı¯ä½¿
    0.09
    Activations Density 0.084%

    No Known Activations