© 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. 21120
    Prev
    Next
    INDEX
    Explanations

    animal welfare and testing

    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
     tÃŃ
    -0.06
    å¤į
    -0.06
    nar
    -0.06
    ÈĽÄĥ
    -0.05
    Uh
    -0.05
    tores
    -0.05
     sekund
    -0.05
    ÙĪدÙĩ
    -0.05
    å¾Ģå¤ĸ
    -0.05
     security
    -0.05
    POSITIVE LOGITS
    æľºåħ³
    0.06
    ä¸ĭæīĭ
    0.06
    raz
    0.06
    evo
    0.06
    exter
    0.06
    åŃĺ
    0.06
    çļĦå®īæİĴ
    0.06
    ç®±
    0.06
    chau
    0.05
     cruelty
    0.05
    Activations Density 0.012%

    No Known Activations