© 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. 44876
    Prev
    Next
    INDEX
    Explanations

    new user

    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
    lez
    -0.07
    å°ĨæĹłæ³ķ
    -0.07
    sWith
    -0.06
    ail
    -0.06
    оÑĤов
    -0.06
    aras
    -0.06
    estin
    -0.06
    uttle
    -0.06
    åĽºå®ļçļĦ
    -0.06
    åĽłä¸ºåľ¨
    -0.06
    POSITIVE LOGITS
    _HOR
    0.08
    ëĭĪëĭ¤
    0.07
    çļĦç¼ĺæķħ
    0.07
    æĺĵæĩĤ
    0.07
    миÑĢа
    0.07
    ündür
    0.07
    å±Ĥåĩºä¸įç©·
    0.07
    ä¸įå°ij人
    0.07
    çĻ»å½ķæŁ¥çľĭ
    0.07
    åıªåIJ¬
    0.07
    Activations Density 0.030%

    No Known Activations