© 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. 21754
    Prev
    Next
    INDEX
    Explanations

    toluene and related compounds

    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
    êµīìŀ¥
    -0.07
    erras
    -0.07
     spad
    -0.07
    꽤
    -0.06
    lashes
    -0.06
    ä¸İçİ°å®ŀ
    -0.06
     spiagg
    -0.06
    isert
    -0.06
    vere
    -0.06
    puesta
    -0.06
    POSITIVE LOGITS
    én
    0.06
    otto
    0.06
     ben
    0.05
    èĤ¯
    0.05
    ind
    0.05
     indifer
    0.05
    åĮ¿
    0.05
    æĮĩ令
    0.05
     Boys
    0.05
    oin
    0.05
    Activations Density 0.013%

    No Known Activations