© 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. 54923
    Prev
    Next
    INDEX
    Explanations

    deletion, insertion, duplication, removal

    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
    ç¨ĭ度
    -0.06
    å½ĵ家
    -0.06
    rieb
    -0.06
    è§ģ人
    -0.06
    èĤ
    -0.06
    iedz
    -0.06
    ()['
    -0.06
    convert
    -0.06
    aning
    -0.06
    ä¸Ģ次åıĪä¸Ģ次
    -0.06
    POSITIVE LOGITS
    æĪĸåĪłéĻ¤
    0.10
    åĪłéĻ¤
    0.08
    è¡¥é½IJ
    0.08
    è¡¥çŁŃ
    0.08
    移éĻ¤
    0.08
    æĪĸ缺
    0.08
    åĪł
    0.08
    å¤ļä½Ļ
    0.08
    /remove
    0.08
    -remove
    0.07
    Activations Density 0.030%

    No Known Activations