© 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. 20472
    Prev
    Next
    INDEX
    Explanations

    focal segmental glomerulosclerosis

    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
    ÑģÑĤÑĢи
    -0.05
    pos
    -0.05
    æ³¥
    -0.05
    è´
    -0.05
     /
    -0.05
    äºĶèĬ±
    -0.05
     desapar
    -0.05
    ’ex
    -0.05
    çĮ
    -0.05
    认å®ļçļĦ
    -0.05
    POSITIVE LOGITS
    ocha
    0.06
    åĦ¿
    0.06
     (('
    0.06
    jär
    0.06
    é¡·
    0.05
    orary
    0.05
     Diret
    0.05
     Ãļltima
    0.05
    å°½æľī
    0.05
    çīĪ车åŀĭ
    0.05
    Activations Density 0.418%

    No Known Activations