© 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. 19024
    Prev
    Next
    INDEX
    Explanations

    mixture of things

    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
    éĶ¦æ¶Ľ
    -0.07
    ç²Ľ
    -0.06
    æĸĩåĵ²
    -0.06
    szt
    -0.06
    quel
    -0.06
    ambito
    -0.06
    Ú¯ÛĮ
    -0.06
    aliste
    -0.06
    å³°åĢ¼æīŃ磩
    -0.06
    å®ħ
    -0.06
    POSITIVE LOGITS
    oss
    0.06
    åı¯ä¹IJ
    0.05
    etag
    0.05
     ÙĪات
    0.05
    çIJĨ
    0.05
    oli
    0.05
    ãĤĵãģ¨
    0.05
    çľ¼çļĦ
    0.05
    éģį
    0.05
    çĦ°
    0.05
    Activations Density 0.001%

    No Known Activations