© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10525
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
    ī
    -0.08
    हन
    -0.08
    opes
    -0.07
    ãģĹãģĭãĤĤ
    -0.07
    ãģĿãģĹãģ¦
    -0.07
     cheva
    -0.07
    idel
    -0.07
     telah
    -0.07
    çĦ¶åIJİçĤ¹åĩ»
    -0.07
    ×ij׾
    -0.07
    POSITIVE LOGITS
    ,
    0.10
    ØĮ
    0.09
    ï¼Į
    0.09
    :
    0.08
    ï¼ĮãĢĬ
    0.07
    åīįèĢħ
    0.07
    àŃį
    0.06
    âĢ¦âĢ¦ãĢĤ
    0.06
    ä¸ĩäºĭ
    0.06
    ä»Ģä¹ĪæĥħåĨµ
    0.06
    Activations Density 0.012%

    No Known Activations