© 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. 33112
    Prev
    Next
    INDEX
    Explanations

    emission, transmitting, radiation

    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
    stem
    -0.07
    adors
    -0.07
    hots
    -0.06
     stem
    -0.06
    anden
    -0.06
    irs
    -0.06
    enary
    -0.06
    峡
    -0.06
     monot
    -0.06
    æľ¬åħ¬ä¼Ĺåı·
    -0.06
    POSITIVE LOGITS
     emission
    0.09
     distant
    0.08
    è¿ľè·Ŀ离
    0.08
     emitting
    0.08
     émissions
    0.08
    ä¼łæĴŃ
    0.08
    éģ¥è¿ľ
    0.08
    è¿ľæĸ¹çļĦ
    0.08
    ombo
    0.07
    éģł
    0.07
    Activations Density 0.001%

    No Known Activations