© 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. 18799
    Prev
    Next
    INDEX
    Explanations

    name, fame, Century, lot, phones, movies, workmanship

    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
     ..."
    -0.07
    ocas
    -0.06
    éļĻ
    -0.06
    æŶéļĶ
    -0.06
    åİķ
    -0.06
    éĺ¶
    -0.06
    l
    -0.06
     lest
    -0.06
    ocl
    -0.06
    plex
    -0.05
    POSITIVE LOGITS
    egade
    0.05
     adolesc
    0.05
    vro
    0.05
    >>::
    0.05
    urre
    0.05
    obod
    0.05
    åķĨä½ı
    0.05
    è¦ģä¹Īæĺ¯
    0.05
    _fold
    0.05
    lements
    0.05
    Activations Density 0.549%

    No Known Activations