© 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. 20003
    Prev
    Next
    INDEX
    Explanations

    I usually do

    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
    åħ¨ä¼ļ
    -0.05
     Soll
    -0.05
     weak
    -0.05
    è¾IJ
    -0.05
     weaker
    -0.05
     typeof
    -0.05
    ä»Ģä¹Īäºĭ
    -0.05
    IGA
    -0.05
    tractor
    -0.05
    æĦŁåĪ°å¾Ī
    -0.05
    POSITIVE LOGITS
    amente
    0.06
    åĪĿæŃ¥
    0.06
    -initial
    0.05
    rau
    0.05
    zat
    0.05
    opot
    0.05
    ilities
    0.05
     tit
    0.05
    ard
    0.05
    جز
    0.05
    Activations Density 0.013%

    No Known Activations