© 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. 19143
    Prev
    Next
    INDEX
    Explanations

    members

    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
     (
    -0.05
    ion
    -0.05
    -0.05
     a
    -0.05
     permanent
    -0.05
     bunch
    -0.05
    èĩªå·±
    -0.05
    енÑĤов
    -0.05
    Ùģس
    -0.04
    家åºŃ
    -0.04
    POSITIVE LOGITS
    lessly
    0.08
    çĦ¶å¤§
    0.08
    تÛĮ
    0.08
    tures
    0.08
    kannya
    0.07
    liness
    0.07
    teenth
    0.07
    sweise
    0.07
    ä»Ģä¹Īåij¢
    0.07
    àµįà´Ł
    0.07
    Activations Density 0.019%

    No Known Activations