© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19033
    Prev
    Next
    INDEX
    Explanations

    information systems and technology

    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
    uhu
    -0.05
    won
    -0.05
    uat
    -0.05
    ãĤ«æľĪ
    -0.04
    ÑĩинÑĥ
    -0.04
    åIJĦä¸į缸åIJĮ
    -0.04
    æĿ¿ä¸Ĭ
    -0.04
     оÑģобенноÑģÑĤей
    -0.04
     Disabilities
    -0.04
     of
    -0.04
    POSITIVE LOGITS
     sekian
    0.07
    åħīæĺ¯
    0.07
    éŁ³åĥı
    0.07
    wealth
    0.06
    à¸Ĥà¹Īาวสาร
    0.06
    è³ĩè¨Ĭ
    0.06
     Information
    0.06
     arrivati
    0.06
     beve
    0.06
    ayette
    0.06
    Activations Density 0.021%

    No Known Activations