© 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. 23971
    Prev
    Next
    INDEX
    Explanations

    controlled reaction or conditions

    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
    иков
    -0.07
    天çĦ¶
    -0.07
     tá»ĩ
    -0.07
    orre
    -0.07
    Plain
    -0.06
    æģķ
    -0.06
     untranslated
    -0.06
    ock
    -0.06
    ãģĦãĤī
    -0.06
    çļĦ天çĦ¶
    -0.06
    POSITIVE LOGITS
    åı¯æݧ
    0.11
     controlled
    0.11
    edly
    0.11
    åı¯å¾ª
    0.11
    controlled
    0.11
    æĶ¾çŁ¢
    0.11
    æľī计åĪĴ
    0.11
    æľīåºıçļĦ
    0.10
    æľīåºı
    0.10
    æľīç»Ħç»ĩ
    0.10
    Activations Density 0.180%

    No Known Activations