© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37591
    Prev
    Next
    INDEX
    Explanations

    Christian community and care

    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
    Negative Logits
    ouz
    -0.07
    size
    -0.07
    assen
    -0.07
    icat
    -0.07
    æĵįä½ľæµģç¨ĭ
    -0.07
    åĤ»çĵľ
    -0.07
    æĬĬäºĭæĥħ
    -0.07
    山人
    -0.06
    åĽ½éĻħä¼ļå±ķä¸Ńå¿ĥ
    -0.06
    Perm
    -0.06
    POSITIVE LOGITS
    æķĻèĤ²çļĦ
    0.10
    çģĮè¾ĵ
    0.10
    æ½ľç§»é»ĺ
    0.10
    æ½ľç§»é»ĺåĮĸ
    0.09
     indo
    0.09
    æķĻåĮĸ
    0.09
    èĤ²äºº
    0.09
    çĨıéĻ¶
    0.09
    éĺµåľ°
    0.09
    å¯ĵæķĻäºİ
    0.09
    Activations Density 0.012%

    No Known Activations