© 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. 17468
    Prev
    Next
    INDEX
    Explanations

    cost or quality descriptors

    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
    ä¸ĢåĪĩ
    -0.05
    æĬĵä½ı
    -0.05
    ibu
    -0.05
    çªģ
    -0.05
    клада
    -0.05
    æĪIJ
    -0.05
    è¾¾åĪ°
    -0.05
    æĸ§
    -0.04
    D
    -0.04
    P
    -0.04
    POSITIVE LOGITS
    mix
    0.06
    ichni
    0.06
    inyin
    0.06
    eningen
    0.06
    pread
    0.06
     докÑĤоÑĢа
    0.06
    彿
    0.06
    è¾ľ
    0.06
    ampp
    0.06
    apl
    0.06
    Activations Density 0.010%

    No Known Activations