© 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. 20961
    Prev
    Next
    INDEX
    Explanations

    å®Ĺæ³å

    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
    lili
    -0.07
    æķħæѤ
    -0.07
    orage
    -0.07
    usi
    -0.07
    ulah
    -0.07
    tics
    -0.06
    .$.
    -0.06
    èµĦ产交æĺĵ
    -0.06
    翼翼
    -0.06
    bria
    -0.06
    POSITIVE LOGITS
    ly
    0.07
    o
    0.06
    ut
    0.06
    care
    0.06
    er
    0.06
    ÑģÑı
    0.06
    ant
    0.06
    ä¸į许
    0.05
    a
    0.05
    fully
    0.05
    Activations Density 0.001%

    No Known Activations