© 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. 18905
    Prev
    Next
    INDEX
    Explanations

    fix examples

    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
    /he
    -0.06
    mee
    -0.06
    mony
    -0.06
    æĹ¢çĦ¶å¦ĤæѤ
    -0.06
    bie
    -0.06
    ä¼ĹæīĢåij¨çŁ¥
    -0.06
    anam
    -0.05
    unky
    -0.05
    меÑĢ
    -0.05
    doing
    -0.05
    POSITIVE LOGITS
    äºİè¡Į
    0.06
    项
    0.05
    äºİä¸Ģ
    0.05
    cina
    0.05
    å¤ĩ
    0.05
     ý
    0.05
     Listing
    0.05
    lj
    0.05
    è¦ģä¸¥æł¼
    0.05
    åħĥåĪ°
    0.05
    Activations Density 0.001%

    No Known Activations