© 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. 19090
    Prev
    Next
    INDEX
    Explanations

    used to provide

    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
    ango
    -0.06
    jal
    -0.06
    åŃIJ
    -0.06
    è¿ĺæĺ¯è¦ģ
    -0.05
     neg
    -0.05
    çĸij
    -0.05
    èį«
    -0.05
    isc
    -0.05
    ç²¾
    -0.05
    åŃĶéĽĢ
    -0.05
    POSITIVE LOGITS
    &(
    0.06
    casting
    0.06
    ersiz
    0.06
    ä¸ŃæĭĽ
    0.06
    &m
    0.06
    æĥ¡
    0.05
    tÃł
    0.05
    åĨįä»İ
    0.05
     pomi
    0.05
    RAINT
    0.05
    Activations Density 0.001%

    No Known Activations