© 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. 20080
    Prev
    Next
    INDEX
    Explanations

    entitled or titled

    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
    yl
    -0.05
    å°¾
    -0.05
     st
    -0.04
    ylation
    -0.04
    çľģå§Ķ
    -0.04
    Release
    -0.04
     A
    -0.04
    antara
    -0.04
    osphate
    -0.04
    常
    -0.04
    POSITIVE LOGITS
    âĢ¦I
    0.07
    cassert
    0.06
    ueb
    0.06
     lul
    0.06
     ÐľÐ¾Ð¸
    0.06
    amor
    0.06
     lirik
    0.06
     mÃŃa
    0.06
     restantes
    0.06
    æĺ¯æĪijçļĦ
    0.06
    Activations Density 0.015%

    No Known Activations