© 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. 19895
    Prev
    Next
    INDEX
    Explanations

    specific use cases

    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
    atang
    -0.06
     trib
    -0.06
    å°ijæķ°
    -0.05
    ãĤ¹ãĤ¿
    -0.05
    çĶµ
    -0.05
    çļĦçĶµ
    -0.05
    ãģŁãģı
    -0.05
    yny
    -0.05
    sten
    -0.05
    ç«ŀ
    -0.05
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.06
    вне
    0.06
    æľŁæľ«
    0.05
    ç²¾ç»ĨåĮĸ管çIJĨ
    0.05
    çªģåĩºéĩįçĤ¹
    0.05
     nearer
    0.05
    gether
    0.05
    以éĻį
    0.05
    ï¸İ
    0.05
     mén
    0.05
    Activations Density 0.001%

    No Known Activations