© 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. 17353
    Prev
    Next
    INDEX
    Explanations

    tirelessly

    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
    inga
    -0.08
    çĶ°åĽŃ
    -0.06
    é¢ĺ
    -0.05
    ing
    -0.05
    ress
    -0.05
     ÙĦازÙħ
    -0.05
    utz
    -0.05
    æīĵä¸Ģ
    -0.05
     доÑĢоге
    -0.05
    ingas
    -0.05
    POSITIVE LOGITS
    bove
    0.08
    ages
    0.06
    穹
    0.06
     lho
    0.06
    ä¿ĥ
    0.06
    onti
    0.06
     Warsz
    0.06
     Warszaw
    0.06
     lluv
    0.06
    è£ķ
    0.06
    Activations Density 0.006%

    No Known Activations