© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19698
    Prev
    Next
    INDEX
    Explanations

    they bring about, can produce, implement, provide, impose

    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
    è§ģäºİ
    -0.06
    el
    -0.06
    称为
    -0.06
    ìĪľ
    -0.06
     lassen
    -0.06
    çĶ±è¢«åijĬ
    -0.06
    ção
    -0.06
    稱çĤº
    -0.06
    plier
    -0.06
     részlet
    -0.06
    POSITIVE LOGITS
    Ùħاش
    0.06
     mas
    0.06
    ä¸įåĪ°
    0.05
     pois
    0.05
    mas
    0.05
    dik
    0.05
    enty
    0.05
    rary
    0.05
    ä¸Ģæĸ¹
    0.05
    好ä¸į好
    0.05
    Activations Density 0.020%

    No Known Activations