© 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. 20808
    Prev
    Next
    INDEX
    Explanations

    analog-to-digital conversion sampling

    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
    请æ±Ĥ
    -0.07
    ลุ
    -0.06
    isto
    -0.06
     hon
    -0.05
     longtime
    -0.05
     oslo
    -0.05
    .SO
    -0.05
     Ùĩد
    -0.05
     Knoxville
    -0.05
    èŤ
    -0.05
    POSITIVE LOGITS
    æĪª
    0.06
     teeth
    0.06
     sampling
    0.06
    å¨Ĩ
    0.05
    Sampling
    0.05
    aved
    0.05
     Sampling
    0.05
    åħ³
    0.05
    éĩĩæł·
    0.05
    studi
    0.05
    Activations Density 0.032%

    No Known Activations