© 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. 20351
    Prev
    Next
    INDEX
    Explanations

    app development contexts

    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
    жда
    -0.06
    ä¹Ķ丹
    -0.05
     اÙĦÙĤائÙħØ©
    -0.05
    çķĮ
    -0.05
    fan
    -0.05
     pasada
    -0.05
    knife
    -0.05
    adı
    -0.05
    erk
    -0.05
     computes
    -0.05
    POSITIVE LOGITS
    visions
    0.06
    rown
    0.06
    InThe
    0.05
    tribu
    0.05
    ator
    0.05
     Senat
    0.05
    thinkable
    0.05
    ä¸Ģæł·çļĦ
    0.05
    æł·çļĦ
    0.05
    asional
    0.05
    Activations Density 0.011%

    No Known Activations