© 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. 19443
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    оÑģÑĤи
    -0.06
    르ì§Ģ
    -0.06
    Undo
    -0.06
    å¤Ħ以
    -0.05
    å°±æĺ¯æĬĬ
    -0.05
    르
    -0.05
    åıªæĺ¯ä¸Ģç§į
    -0.05
     atas
    -0.05
     rembourse
    -0.05
    ür
    -0.05
    POSITIVE LOGITS
    atts
    0.07
    æIJŃ建äºĨ
    0.06
    heads
    0.06
    elow
    0.06
    usul
    0.05
     sätt
    0.05
     lot
    0.05
    orique
    0.05
    quire
    0.05
    çŁ¿çī©è´¨
    0.05
    Activations Density 0.000%

    No Known Activations