© 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. 17019
    Prev
    Next
    INDEX
    Explanations

    ambition and ambitious plans

    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
    åľ¨æİ¥åıĹ
    -0.07
    onde
    -0.06
    кÑĤ
    -0.06
    大å§IJ
    -0.06
    izen
    -0.05
    ÙĤاء
    -0.05
    oz
    -0.05
    lez
    -0.05
    whelming
    -0.05
    AAD
    -0.05
    POSITIVE LOGITS
    üst
    0.06
    ä½łçļĦåIJįåŃĹ
    0.06
    antly
    0.06
    اÙĦØ©
    0.06
    æŁĵ
    0.05
    ayat
    0.05
    åĩĮäºij
    0.05
     sync
    0.05
    yorsunuz
    0.05
    gerald
    0.05
    Activations Density 0.004%

    No Known Activations