© 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. 23707
    Prev
    Next
    INDEX
    Explanations

    chromium, organic, lead, animal testing

    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
     Berger
    -0.07
    appl
    -0.07
     Presup
    -0.07
     spont
    -0.07
    失æģĭ
    -0.06
     непÑĢ
    -0.06
    æĪ¿ç§Ł
    -0.06
    ideos
    -0.06
    ä¸įæĮī
    -0.06
    èŀįèŀį
    -0.06
    POSITIVE LOGITS
    çļĦå®īåħ¨æĢ§
    0.10
    æĹłå®³
    0.10
     unacceptable
    0.09
     harmful
    0.09
     اÙĦسÙĦاÙħØ©
    0.09
    å®īåħ¨æĢ§
    0.09
    çļĦåį±å®³
    0.08
    çļĦå®īåħ¨
    0.08
     safety
    0.08
    åģ¥åº·å®īåħ¨
    0.08
    Activations Density 0.271%

    No Known Activations