© 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. 8502
    Prev
    Next
    INDEX
    Explanations

    single digit, constant exponential

    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
    èĢģäºĨ
    -0.08
    uldig
    -0.07
     constituted
    -0.07
    attu
    -0.07
    ä¼ģä¸ļæıIJä¾Ľ
    -0.07
     lÃŃmite
    -0.07
    ç»Ī究
    -0.06
    ofer
    -0.06
    éĩĩ
    -0.06
    æŀĦæĪIJçļĦ
    -0.06
    POSITIVE LOGITS
    å°½åı¯èĥ½
    0.10
    å°½éĩı
    0.10
     hopefully
    0.09
    hopefully
    0.09
    å°½åı¯èĥ½çļĦ
    0.09
    ä¸įåĨį
    0.09
    å°½åı¯èĥ½åľ°
    0.08
    便äºİ
    0.08
    åĬĽäºī
    0.08
    ä¸ĵ
    0.08
    Activations Density 0.028%

    No Known Activations