© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21071
    Prev
    Next
    INDEX
    Explanations

    sustainable applications and outcomes

    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
    estar
    -0.06
    estes
    -0.06
    åķ¬
    -0.06
    ial
    -0.06
    umat
    -0.06
    ester
    -0.06
    次çļĦ
    -0.06
    estra
    -0.06
    imate
    -0.05
    Ø©
    -0.05
    POSITIVE LOGITS
    er
    0.09
    ر
    0.08
    o
    0.07
    о
    0.06
    Ùĩ
    0.06
    宣è¨Ģ
    0.06
    anse
    0.06
    zyn
    0.06
    erat
    0.06
    ance
    0.06
    Activations Density 0.002%

    No Known Activations