© 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. 19099
    Prev
    Next
    INDEX
    Explanations

    this or self referencing fields

    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
    oved
    -0.06
    ductive
    -0.06
    Resta
    -0.06
    éĽĨåħ¨
    -0.06
    FML
    -0.06
    éģģ
    -0.06
    olda
    -0.06
    ÑĮеÑĤ
    -0.06
    usione
    -0.06
    å¾ĢæĺĶ
    -0.06
    POSITIVE LOGITS
    owski
    0.05
    stücks
    0.05
    éĹ´çļĦ
    0.05
     ÑĥÑĩаÑģÑĤи
    0.05
    æłĩåĩĨ
    0.05
    çī¹æ®ĬæĢ§
    0.05
    alli
    0.05
     mor
    0.05
    西åħ°
    0.05
    наÑģÑĤоÑı
    0.05
    Activations Density 0.003%

    No Known Activations