© 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. 44784
    Prev
    Next
    INDEX
    Explanations

    I assistance

    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
    ropped
    -0.07
    доб
    -0.07
    éĩįä¸Ńä¹ĭéĩį
    -0.07
    éĿłå·¦
    -0.07
     Crosby
    -0.06
    è¦ģæī¾
    -0.06
    åijĬ
    -0.06
     Vernon
    -0.06
    reu
    -0.06
    è··
    -0.06
    POSITIVE LOGITS
    .Generate
    0.08
     запÑĢо
    0.07
    æĻºèĥ½
    0.07
    亿ä¸ĩ
    0.07
    åĬ©æīĭ
    0.07
    äºĶåįĥå¹´
    0.07
    Lov
    0.07
    ç®Ĺæ³ķ
    0.07
     algorithms
    0.07
     assisted
    0.07
    Activations Density 0.035%

    No Known Activations