© 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. 21798
    Prev
    Next
    INDEX
    Explanations

    prior expressed wishes

    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
    èī°
    -0.06
     Kho
    -0.05
    éĢīä¸Ģ
    -0.05
     Interface
    -0.05
    欣
    -0.05
    ou
    -0.05
    auty
    -0.05
     interface
    -0.05
    Âł
    -0.05
     Choice
    -0.05
    POSITIVE LOGITS
    èµ°éģį
    0.06
     integrale
    0.06
    amed
    0.06
    ezi
    0.06
     عÙĨÙĩا
    0.06
     &(
    0.06
    лÑĥм
    0.06
    ç¹Ķ
    0.06
    èµ·åı¸
    0.06
     uncomp
    0.06
    Activations Density 0.003%

    No Known Activations