© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    Is this or are you

    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
    ä¸Ģ鸣
    -0.09
    ä¸ĵå¿ĥ
    -0.08
    çļĦæľīåħ³è§Ħå®ļ
    -0.08
    ר×ķת
    -0.08
    ä¸ĩ家
    -0.07
    ussi
    -0.07
    说åIJ§
    -0.07
    Besides
    -0.07
    azi
    -0.07
    ads
    -0.07
    POSITIVE LOGITS
     latter
    0.09
    åIJİèĢħ
    0.09
     thereof
    0.09
    åīįèĢħ
    0.09
    对æѤ
    0.09
     isso
    0.08
    以æѤ
    0.08
    æĺ¯å¦ĤæѤ
    0.08
    以æŃ¤ä¸º
    0.08
    æĺ¯è¿Ļ个
    0.08
    Activations Density 0.148%

    No Known Activations