© 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. 20158
    Prev
    Next
    INDEX
    Explanations

    specifically followed by comma

    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
     exig
    -0.05
     eset
    -0.05
    临
    -0.05
     bord
    -0.05
    ali
    -0.05
    -top
    -0.05
     erg
    -0.05
     market
    -0.05
     rop
    -0.05
    apar
    -0.05
    POSITIVE LOGITS
    anto
    0.06
    èĩ³å°ij
    0.06
    主è¦ģåĪĨ为
    0.06
     firstly
    0.06
    大约
    0.06
    oriously
    0.06
    ovol
    0.06
    è¦ģä¹Ī
    0.06
    å°ijãģªãģıãģ¨ãĤĤ
    0.06
    使çĶ¨çļĦæĺ¯
    0.06
    Activations Density 0.084%

    No Known Activations