© 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. 42565
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions

    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
    irl
    -0.07
    uto
    -0.07
    idl
    -0.07
    æĪij们éĢļè¿ĩ
    -0.07
    èĥ½å¤ŁéĢļè¿ĩ
    -0.07
    brig
    -0.07
    èĢĮä¸Ķ
    -0.07
    edBy
    -0.07
    ehme
    -0.06
    ä¹Łåı¯èĥ½æĺ¯
    -0.06
    POSITIVE LOGITS
    ä¼ļåıijçİ°
    0.15
    å°±ä¼ļåıijçİ°
    0.14
    åıijçİ°æľī
    0.14
    ä½łä¼ļåıijçİ°
    0.13
    åıijçİ°åľ¨
    0.12
    åı¯ä»¥åıijçİ°
    0.11
    ç»ĵæŀľä¸º
    0.11
    à¸ŀà¸ļวà¹Īา
    0.11
    ç»ĵæŀľæĺ¾ç¤º
    0.10
     reveals
    0.10
    Activations Density 0.200%

    No Known Activations