© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46635
    Prev
    Next
    INDEX
    Explanations

    documents, objects, spaces, intention

    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
    andi
    -0.07
    nict
    -0.06
    åIJĮ缣
    -0.06
    éĩĮéĿ¢æľī
    -0.06
    纵
    -0.06
    ä¸ĩå¹´
    -0.06
    æ¼ĶæĪı
    -0.06
    å¯Įäºİ
    -0.06
     glo
    -0.06
    å½»
    -0.06
    POSITIVE LOGITS
    ilon
    0.09
    дÑĥм
    0.08
    å°Ķ夫
    0.08
     вдÑĢÑĥг
    0.08
    iji
    0.08
    VEL
    0.07
    جد
    0.07
    ble
    0.07
     repente
    0.07
    posito
    0.07
    Activations Density 0.304%

    No Known Activations