© 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. 58042
    Prev
    Next
    INDEX
    Explanations

    transduction pathways

    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
     fug
    -0.08
    å®īåİ¿
    -0.08
    åĪ»æĦı
    -0.08
    å¥Ħ
    -0.07
     cubic
    -0.07
     planned
    -0.07
     kub
    -0.07
     ÑĤеÑħни
    -0.07
    çħŀ
    -0.06
    itemap
    -0.06
    POSITIVE LOGITS
     signaling
    0.11
    æ¿Ģæ´»
    0.10
     activation
    0.10
    ä¿¡åı·
    0.10
     activating
    0.10
     messenger
    0.10
     signalling
    0.09
     signal
    0.09
    signal
    0.09
    (signal
    0.09
    Activations Density 0.147%

    No Known Activations