© 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. 62570
    Prev
    Next
    INDEX
    Explanations

    company, business, or legal entity

    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
    ä»»åĬ³
    -0.09
    .Entry
    -0.08
    纲
    -0.07
    uÅĤ
    -0.07
     Terl
    -0.07
    ione
    -0.07
    æĢĢéĩĮ
    -0.07
    åĨľåķĨéĵ¶è¡Į
    -0.07
    稳ä½ı
    -0.07
    èģĶ缣
    -0.07
    POSITIVE LOGITS
    çļĦ身
    0.06
    ä»Ģä¹Īéĥ½æ²¡
    0.06
    çľĭä¸Ń
    0.06
    oger
    0.06
    åħĭ鼷
    0.06
    çĶŁäº§éĶĢåĶ®
    0.06
    æ¡Ī件ä¸Ń
    0.06
    éĿŀ常çļĦ
    0.06
    å°Ĩèĩªå·±çļĦ
    0.06
     closely
    0.06
    Activations Density 0.010%

    No Known Activations