© 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. 20203
    Prev
    Next
    INDEX
    Explanations

    razole 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
    cket
    -0.07
    ÑĤÑĢе
    -0.07
    gados
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.06
    à§Ģয়
    -0.06
    tez
    -0.06
    izer
    -0.06
    truc
    -0.06
    apult
    -0.06
    arine
    -0.06
    POSITIVE LOGITS
    ×Ļ×Ŀ
    0.07
    ات
    0.07
    s
    0.06
    esistenza
    0.06
    onder
    0.06
    loth
    0.06
    illage
    0.05
    çĶŁäº§å»ºè®¾åħµåĽ¢
    0.05
     sider
    0.05
    sider
    0.05
    Activations Density 0.003%

    No Known Activations