© 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. 60350
    Prev
    Next
    INDEX
    Explanations

    unilateral or asymmetric side

    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
    æĮĩ纹
    -0.08
    å¯ĨéĽĨ
    -0.07
    ç³ł
    -0.07
     à¦ħন
    -0.06
    段éļİ
    -0.06
    rick
    -0.06
    åĪ°å¤Ħ
    -0.06
    稳
    -0.06
    ä¸Ģå±Ĥ
    -0.06
     layered
    -0.06
    POSITIVE LOGITS
    ä¸Ģ侧
    0.17
    ä¸į对称
    0.15
    _side
    0.15
    çļĦä¸Ģ侧
    0.15
     asymmetric
    0.15
    åįĬè¾¹
    0.14
     asym
    0.14
     unilateral
    0.14
     side
    0.14
    -side
    0.13
    Activations Density 0.340%

    No Known Activations