© 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. 11115
    Prev
    Next
    INDEX
    Explanations

    on the safe 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
    éĤ£ä¹Ī容æĺĵ
    -0.08
    óz
    -0.08
    สà¸Ķ
    -0.08
    è½»èĢĮæĺĵ举
    -0.07
    æµ´
    -0.07
    æĥ¬æĦı
    -0.07
    çIJĨæīĢ
    -0.07
    æģ°å¥½
    -0.07
    è¿Ļä¹Īå¿«
    -0.07
     conveniently
    -0.07
    POSITIVE LOGITS
    èµ·è§ģ
    0.10
    shal
    0.07
    assi
    0.07
     Murphy
    0.07
    稳妥
    0.07
     doubts
    0.07
    æ½ĺ
    0.06
    å¯Ĵ
    0.06
     against
    0.06
     suspicions
    0.06
    Activations Density 0.010%

    No Known Activations