© 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. 4787
    Prev
    Next
    INDEX
    Explanations

    interaction via specific binding

    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
     непÑĢо
    -0.08
    æĻ®åıĬ
    -0.07
     chang
    -0.07
    åŃķèĤ²
    -0.07
    çĶ±å¸Ĥ
    -0.06
    çłį
    -0.06
    éĻ¡
    -0.06
    inz
    -0.06
    å²Ķ
    -0.06
    ç»´æĬ¤
    -0.06
    POSITIVE LOGITS
    çļĦ亲
    0.10
    äºĴè¡¥
    0.10
    å½¼æѤçļĦ
    0.09
    å½¼æѤ
    0.09
     oppos
    0.09
     attraction
    0.08
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.08
    ä¼ĺåĬ¿äºĴè¡¥
    0.08
    avid
    0.08
    亲
    0.08
    Activations Density 0.040%

    No Known Activations