© 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. 8152
    Prev
    Next
    INDEX
    Explanations

    tert.butoxide, numbers, Dolinský

    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
    umpf
    -0.07
    amia
    -0.07
     tro
    -0.06
    amus
    -0.06
    对äºİè¿ĻäºĽ
    -0.06
     prom
    -0.06
    æľ¬ç½ijç«Ļ
    -0.06
    ables
    -0.06
    纳德
    -0.06
    èºı
    -0.06
    POSITIVE LOGITS
    å¼¹
    0.08
    -symbol
    0.07
    gem
    0.07
    ä¼ģ
    0.06
    iesta
    0.06
     bum
    0.06
    ITI
    0.06
     korist
    0.06
    uby
    0.06
     uchar
    0.06
    Activations Density 0.009%

    No Known Activations