© 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. 18895
    Prev
    Next
    INDEX
    Explanations

    evidence and studies

    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
    éģį
    -0.06
    esis
    -0.06
    yecto
    -0.05
    à¹ģ
    -0.05
    set
    -0.05
    úcar
    -0.05
    çļĦéĤ£ä¸ªäºº
    -0.05
     Bas
    -0.05
     Pets
    -0.05
    isis
    -0.05
    POSITIVE LOGITS
    oplast
    0.06
    actions
    0.06
     infinity
    0.06
    Õ²
    0.06
    åı«éĨĴ
    0.06
    ilian
    0.06
    infinity
    0.05
    åĬŁ
    0.05
    Infinity
    0.05
    qv
    0.05
    Activations Density 0.044%

    No Known Activations