© 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. 20327
    Prev
    Next
    INDEX
    Explanations

    create, creates, created

    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
    zed
    -0.05
    DT
    -0.05
     before
    -0.05
    æĮ¯
    -0.05
    D
    -0.05
     yourselves
    -0.05
     stuck
    -0.04
    åĬ¨
    -0.04
     after
    -0.04
    POSITIVE LOGITS
    urin
    0.07
    aktu
    0.07
    以æľįåĬ¡
    0.07
    intai
    0.07
    以éĢĤåºĶ
    0.06
    illas
    0.06
    çĶ¨æĪ·ä½¿çĶ¨
    0.06
     kte
    0.06
     Associates
    0.06
    ento
    0.06
    Activations Density 0.009%

    No Known Activations