© 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. 31102
    Prev
    Next
    INDEX
    Explanations

    weak bonds

    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
     basically
    -0.09
    åŁºæľ¬ä¸Ĭ
    -0.08
     âĢ¦
    -0.07
    æľīä¸ĢäºĽ
    -0.07
     contemplated
    -0.07
     usw
    -0.07
     sometime
    -0.07
    ä¹Łå°±æĺ¯
    -0.07
    âĢ¦âĢ¦
    -0.07
    çĽ¸å¯¹æĿ¥è¯´
    -0.07
    POSITIVE LOGITS
    æĦıä¹īéĩį大
    0.09
    threat
    0.09
    zis
    0.08
    çļĦåħ¨çIJĥ
    0.08
    æīįæĺİçĻ½
    0.08
    çİĩè¾¾
    0.08
     ironically
    0.08
    åħ³åģľ
    0.08
     hardcoded
    0.08
    upe
    0.08
    Activations Density 0.001%

    No Known Activations