© 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. 20337
    Prev
    Next
    INDEX
    Explanations

    `end` + `ocard` or `the` + `coat`

    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
    os
    -0.06
    åIJĦ级åħļå§Ķ
    -0.05
     organ
    -0.05
    UFFER
    -0.05
    oran
    -0.05
    æİĴ
    -0.05
    มà¸Ļ
    -0.05
    åij¨ä¸ī
    -0.05
     pove
    -0.05
    à¹Īาà¸Ļัà¹īà¸Ļ
    -0.05
    POSITIVE LOGITS
    å¹´å°±
    0.06
    etics
    0.06
    jug
    0.06
    eties
    0.06
     Arag
    0.06
    etic
    0.05
    teau
    0.05
     contag
    0.05
    ]|[
    0.05
    æĺŃ
    0.05
    Activations Density 0.006%

    No Known Activations