© 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. 18652
    Prev
    Next
    INDEX
    Explanations

    user community size

    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
    esen
    -0.06
    alli
    -0.06
    oyer
    -0.06
    /E
    -0.06
    باÙĨ
    -0.06
    ospital
    -0.05
    åĴĮéĶĢåĶ®
    -0.05
     Different
    -0.05
    avl
    -0.05
     Likely
    -0.05
    POSITIVE LOGITS
    uerte
    0.06
    ียà¸Ķ
    0.06
    æĮĿ
    0.06
    Ñĥг
    0.06
     portion
    0.05
    ä¹į
    0.05
     bothers
    0.05
     verh
    0.05
    dut
    0.05
    itude
    0.05
    Activations Density 0.013%

    No Known Activations