© 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. 18207
    Prev
    Next
    INDEX
    Explanations

    font-family declarations

    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
    Úĺ
    -0.06
    æ´¾
    -0.05
    çĩİ
    -0.05
    jos
    -0.05
    æĶ¾è¿ĩ
    -0.05
    aramel
    -0.05
    å®Ļ
    -0.05
     gên
    -0.05
    Ùģس
    -0.05
    argomento
    -0.05
    POSITIVE LOGITS
    ents
    0.06
    aine
    0.06
    æĨ¨
    0.06
    te
    0.06
    Åĵur
    0.05
     handful
    0.05
    tez
    0.05
     дÑĢ
    0.05
    жди
    0.05
    uja
    0.05
    Activations Density 0.001%

    No Known Activations