© 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. 21275
    Prev
    Next
    INDEX
    Explanations

    built-in

    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
    o
    -0.09
    ar
    -0.08
    аÑĢ
    -0.07
    ed
    -0.06
    ÑģÑı
    -0.06
    as
    -0.06
    u
    -0.06
    cents
    -0.06
    ted
    -0.06
    ë¶Ģë¡ľ
    -0.06
    POSITIVE LOGITS
    izations
    0.06
    ousel
    0.06
    isian
    0.06
    eness
    0.06
    åĨĽå§Ķ
    0.06
    foro
    0.06
    åĮĸæĪIJ
    0.06
     ute
    0.05
    ãĥ¼
    0.05
    andise
    0.05
    Activations Density 0.011%

    No Known Activations