© 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. 19173
    Prev
    Next
    INDEX
    Explanations

    classification, prediction, or evaluation

    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
    –and
    -0.07
     emer
    -0.07
    ched
    -0.06
    çªģåıij
    -0.06
    αιν
    -0.06
    å®ļæŶ
    -0.06
     asynchronously
    -0.06
    ksen
    -0.06
    aka
    -0.06
    kers
    -0.06
    POSITIVE LOGITS
    ze
    0.05
    éc
    0.05
     (
    0.05
    '
    0.05
     from
    0.04
    è¿ĺæĺ¯ä»¥
    0.04
     h
    0.04
     squ
    0.04
     ↵
    0.04
    صد
    0.04
    Activations Density 0.001%

    No Known Activations