© 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. 20157
    Prev
    Next
    INDEX
    Explanations

    "USA TODAY"

    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
    æĿ¡
    -0.06
     Rel
    -0.05
    äºİè¡Į
    -0.05
    ستر
    -0.05
    纵
    -0.05
    åī§
    -0.05
     rel
    -0.05
    表
    -0.05
    åĴ¬çīĻåĪĩ
    -0.05
    strate
    -0.05
    POSITIVE LOGITS
    uppe
    0.06
    ued
    0.05
    ob
    0.05
    attel
    0.05
    hold
    0.05
    пил
    0.05
    antry
    0.05
    egah
    0.05
    ogado
    0.05
     hold
    0.05
    Activations Density 0.017%

    No Known Activations