© 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. 64614
    Prev
    Next
    INDEX
    Explanations

    .com/.co domains

    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
     Tweets
    -0.09
     Tweet
    -0.08
     tweeting
    -0.08
    æĸ°éĹ»èĪĨæĥħ
    -0.07
    ãĥĦãĤ¤ãĥ¼ãĥĪ
    -0.07
    èĢIJ
    -0.07
    zung
    -0.07
    æŃ¦ä¾łä¿®çľŁ
    -0.07
    åıijè¡¨åľ¨
    -0.07
     tweets
    -0.07
    POSITIVE LOGITS
    çŃīå¹³åı°
    0.12
    .com
    0.12
    ®
    0.10
    å¹³åı°ä¸Ĭ
    0.08
    .co
    0.08
    ®,
    0.08
    usercontent
    0.08
    .COM
    0.08
    å¹³åı°çļĦ
    0.08
    ä¸ĬçļĦ
    0.07
    Activations Density 0.307%

    No Known Activations