© 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. 56242
    Prev
    Next
    INDEX
    Explanations

    user identification

    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
    ains
    -0.08
    å®ĥ们æĺ¯
    -0.08
    phan
    -0.08
    女éĥİ
    -0.08
    xt
    -0.08
    âu
    -0.08
    ä¸ĵ家们
    -0.08
    åѦçĶŁä»¬
    -0.08
    æĪĺ士们
    -0.07
    为人们
    -0.07
    POSITIVE LOGITS
     who
    0.11
     whom
    0.10
    who
    0.09
     personal
    0.08
    å§ĵåIJį
    0.08
     Who
    0.08
     whose
    0.08
    æĺ¯è°ģ
    0.08
     alias
    0.08
    个人
    0.08
    Activations Density 0.366%

    No Known Activations