© 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. 21349
    Prev
    Next
    INDEX
    Explanations

    continue reading

    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
     simplest
    -0.06
    å¤Ł
    -0.06
    天秤
    -0.06
    ospace
    -0.05
    anders
    -0.05
    æľĢç®ĢåįķçļĦ
    -0.05
    禧
    -0.05
    èĩªåľ¨
    -0.05
     easiest
    -0.05
    éĺ²çĸ«æݪæĸ½
    -0.05
    POSITIVE LOGITS
     consé
    0.05
     Through
    0.05
    through
    0.05
     exclusivement
    0.05
     exclusivamente
    0.05
    lang
    0.05
    -ext
    0.05
     lika
    0.05
    ites
    0.05
    ISC
    0.05
    Activations Density 0.011%

    No Known Activations