© 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. 20050
    Prev
    Next
    INDEX
    Explanations

    ographic or orical terms

    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
    naire
    -0.10
    ution
    -0.07
    æĵį
    -0.07
    otta
    -0.07
    naires
    -0.07
    krét
    -0.07
    APPER
    -0.06
    vation
    -0.06
    wak
    -0.06
    à¸ģรุ
    -0.06
    POSITIVE LOGITS
    alloc
    0.06
    SY
    0.05
    èĢĮéļıçĿĢ
    0.05
     wholly
    0.05
    æīĢ使çĶ¨çļĦ
    0.05
    acion
    0.05
    ä¸Ģéĥİ
    0.05
    oc
    0.05
    INCLUDING
    0.04
    esy
    0.04
    Activations Density 0.002%

    No Known Activations