© 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. 14619
    Prev
    Next
    INDEX
    Explanations

    contrasting counterparts, ours, theirs

    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
    é²²
    -0.08
    ắng
    -0.08
    гона
    -0.07
    年头
    -0.07
     ocas
    -0.07
    pum
    -0.07
     convocatoria
    -0.07
     اÙĦÙħبارÙĥ
    -0.07
     êµŃëĤ´ìĻ¸
    -0.07
    ople
    -0.07
    POSITIVE LOGITS
    缸æ¯Ķä¹ĭä¸ĭ
    0.09
     contrasting
    0.08
     ours
    0.08
     theirs
    0.08
    对æ¯Ķ
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    çĭ¬æľī
    0.07
    æݥ轨
    0.07
    ours
    0.07
     counterparts
    0.07
    Activations Density 0.144%

    No Known Activations