© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50288
    Prev
    Next
    INDEX
    Explanations

    way to say

    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
    æĽ´æĺ¯ä¸Ģ
    -0.07
    ehr
    -0.07
    iep
    -0.07
    anke
    -0.07
     Opis
    -0.06
    oes
    -0.06
    å¿ĺæĢĢ
    -0.06
    emente
    -0.06
    iid
    -0.06
    utorials
    -0.06
    POSITIVE LOGITS
    è¿Ļ个éģĵçIJĨ
    0.07
    强è°ĥäºĨ
    0.07
    견
    0.07
     Tid
    0.07
    é«ĺå±Ĥ次
    0.07
    âĢ¦the
    0.06
    âĢ¦it
    0.06
    .masks
    0.06
    imity
    0.06
    强è°ĥ
    0.06
    Activations Density 0.002%

    No Known Activations