© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21716
    Prev
    Next
    INDEX
    Explanations

    place names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     turnover
    -0.05
     E
    -0.05
    åıĺ缸
    -0.05
    gelt
    -0.05
    è¿Ļé¦ĸ
    -0.05
    rah
    -0.05
     P
    -0.05
    æŀģäºĨ
    -0.05
    è¿Ļæĸ¹éĿ¢
    -0.05
    å°ĨæĿ¥
    -0.04
    POSITIVE LOGITS
    kau
    0.07
    amment
    0.07
    lobal
    0.07
     mues
    0.06
     aray
    0.06
    ickey
    0.06
    rou
    0.06
    lega
    0.06
    èį¯
    0.06
     Sejumlah
    0.06
    Activations Density 0.009%

    No Known Activations