© 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. 7347
    Prev
    Next
    INDEX
    Explanations

    cycles per degree

    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
    æĢİä¹Īæł·äºĨ
    -0.06
    çĨŁ
    -0.06
    ente
    -0.06
    lings
    -0.06
    eden
    -0.06
    ida
    -0.06
    èĩªçĦ¶èĢĮçĦ¶
    -0.06
    åŁºæľ¬çŁ¥è¯Ĩ
    -0.06
    ajo
    -0.06
    1
    -0.06
    POSITIVE LOGITS
    âĢ¦]
    0.08
    пÑĢиÑı
    0.08
    Õ¶
    0.08
    æĺµ
    0.08
    ofilm
    0.08
    çĿIJ
    0.08
    onaldo
    0.07
    losures
    0.07
    unki
    0.07
    人åĵģ
    0.07
    Activations Density 0.072%

    No Known Activations