© 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. 15997
    Prev
    Next
    INDEX
    Explanations

    evaluations and states

    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
     ãĢģ
    -0.07
    çĦ¶
    -0.07
    å°±æĺ¯è¿Ļä¹Ī
    -0.06
    ä»ħæѤ
    -0.06
     lege
    -0.06
    åIJ¾
    -0.06
     СооÑĤвеÑĤÑģÑĤвенно
    -0.06
    对åħ¶
    -0.06
    å°±è¿Ļæł·
    -0.06
     consistently
    -0.06
    POSITIVE LOGITS
     ведÑĮ
    0.09
    º¼
    0.09
     whereby
    0.08
     denn
    0.08
    éĶµ
    0.08
    زة
    0.08
     ÐĴедÑĮ
    0.07
     ÙģÙģÙĬ
    0.07
    ertext
    0.07
     yaitu
    0.07
    Activations Density 0.045%

    No Known Activations