© 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. 20188
    Prev
    Next
    INDEX
    Explanations

    asymmetry and biases

    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
    æĭħ
    -0.07
    解åĨ³
    -0.07
    èħ¾
    -0.07
    ogli
    -0.07
    çľºæľĽ
    -0.06
    ufe
    -0.06
    æ²ŁéĢļ
    -0.06
    æ°´
    -0.06
     solution
    -0.06
     Tender
    -0.06
    POSITIVE LOGITS
    ä¸į对称
    0.09
    飾
    0.09
     asym
    0.08
     Ñĩоло
    0.07
    交çĶµ
    0.07
     biases
    0.07
     asymmetric
    0.07
    yment
    0.07
    ctal
    0.07
     onRequest
    0.07
    Activations Density 0.011%

    No Known Activations