© 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. 17764
    Prev
    Next
    INDEX
    Explanations

    inhibitory effects

    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
    æģĻ
    -0.07
    ظر
    -0.07
     quarters
    -0.06
    å¥ĩè§Ĥ
    -0.06
     datum
    -0.06
    ç»´æĿĥ
    -0.06
    еÑģо
    -0.06
    kas
    -0.06
     resized
    -0.06
    æī¿åıĹèĥ½åĬĽ
    -0.06
    POSITIVE LOGITS
     indirectly
    0.11
    ä¸Ĭè°ĥ
    0.10
    æĬijåĪ¶
    0.10
    ä¸ĭè°ĥ
    0.09
     opposing
    0.09
    è°ĥèĬĤ
    0.09
     inhib
    0.09
     inhibition
    0.09
     mediated
    0.09
    éĹ´æİ¥
    0.08
    Activations Density 0.315%

    No Known Activations