© 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. 13526
    Prev
    Next
    INDEX
    Explanations

    Privacy, Value, magnet, sun, amber, clip

    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
    Ñħо
    -0.07
    วล
    -0.07
    æºī
    -0.07
    æ¯Ĺ
    -0.07
    çļĦæŶéĹ´éĩĮ
    -0.07
    irme
    -0.07
    çľĭæ¸ħæ¥ļ
    -0.07
    cules
    -0.06
    yarat
    -0.06
     Hook
    -0.06
    POSITIVE LOGITS
    æį¢æĪIJ
    0.08
    软
    0.07
    éĿŀæłĩ
    0.06
    çī¹æľīçļĦ
    0.06
    ïºİ
    0.06
    论
    0.06
    èĩªå¸¦çļĦ
    0.06
    ç½Ħ
    0.06
    æĭĨè£ħ
    0.06
    å·¨
    0.06
    Activations Density 0.002%

    No Known Activations