© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16906
    Prev
    Next
    INDEX
    Explanations

    sponge or porous structures

    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
    st
    -0.06
    ãĤģ
    -0.06
     altına
    -0.06
    arg
    -0.06
    l
    -0.06
    ãĤģãģŁ
    -0.06
    é©»åįİ
    -0.06
    ither
    -0.05
    anic
    -0.05
    (IR
    -0.05
    POSITIVE LOGITS
    ponge
    0.07
    bruk
    0.06
    ÙĪجÙĩ
    0.06
    orro
    0.06
    åIJ¹
    0.06
     retor
    0.06
    éĩı大
    0.06
     اÙĦØ£ÙĤصÙī
    0.06
    ible
    0.06
     espon
    0.06
    Activations Density 0.011%

    No Known Activations