© 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. 59877
    Prev
    Next
    INDEX
    Explanations

    remaining parts

    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
    amak
    -0.07
    å±Ĭãģij
    -0.07
    /cc
    -0.07
    稼
    -0.07
    稽
    -0.06
    uso
    -0.06
    English
    -0.06
    èĹIJ
    -0.06
    ibo
    -0.06
    è¿Ľå±ķæĥħåĨµ
    -0.06
    POSITIVE LOGITS
    åħ¶ä½Ļ
    0.09
     оÑģÑĤалÑĮнÑĭÑħ
    0.08
     afterward
    0.08
     remaining
    0.08
    åī©ä¸ĭçļĦ
    0.07
    åıĸèĢĮ代ä¹ĭ
    0.07
     оÑģÑĤалÑĮнÑĭе
    0.07
     mila
    0.07
     restante
    0.07
    åī©ä½Ļ
    0.07
    Activations Density 0.029%

    No Known Activations