© 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. 34859
    Prev
    Next
    INDEX
    Explanations

    scientific journals and fields

    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
    ikka
    -0.06
    acker
    -0.06
     Newest
    -0.06
    次åĽŀ
    -0.06
    .arg
    -0.06
    çľ¼çº¿
    -0.06
    åħ¨éĥ¨éĥ½
    -0.06
     happiest
    -0.06
    à¹Ģà¸Ħà¸Ļ
    -0.06
    éĩįå¤į
    -0.06
    POSITIVE LOGITS
    alaman
    0.08
     INFORMA
    0.08
     Cas
    0.08
    ksam
    0.07
    lete
    0.07
    arz
    0.07
    çIJĨçļĦ
    0.07
    éģĩè§ģ
    0.07
    åĬ¨è¾Ħ
    0.07
    åĴĮçĶŁæ´»
    0.07
    Activations Density 0.009%

    No Known Activations