© 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. 21097
    Prev
    Next
    INDEX
    Explanations

    information and resources

    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
    åīª
    -0.06
     fu
    -0.06
    interno
    -0.06
    оÑĤов
    -0.06
     delantero
    -0.06
     factorial
    -0.05
     internacion
    -0.05
    ena
    -0.05
    native
    -0.05
    天æĸĩ
    -0.05
    POSITIVE LOGITS
    ä»İè¿Ļ个
    0.07
    è¦ģä»İ
    0.07
    èĥ½ä»İ
    0.07
    ä»İä¸Ń
    0.07
     from
    0.07
    ä¼ļä»İ
    0.07
    ä»İæĹł
    0.06
    åı¯ä»¥ä»İ
    0.06
    ä»İ
    0.06
    æĪijä»İ
    0.06
    Activations Density 0.142%

    No Known Activations