© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 18061
    Prev
    Next
    INDEX
    Explanations

    even though

    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
    roi
    -0.06
    вед
    -0.06
    оÑĢÑĤа
    -0.05
    ä»Ģä¹ĪæĥħåĨµ
    -0.05
    èħ¹
    -0.05
    king
    -0.05
    ÑĤа
    -0.05
    æ»Ķ
    -0.05
    Õ¸ÖĢ
    -0.05
    yr
    -0.05
    POSITIVE LOGITS
    éĤ£ä¹Ī大
    0.06
    款
    0.06
     overarching
    0.05
    ÑģÑĤеÑģÑĤвенно
    0.05
    coni
    0.05
    ä¹Łå¸ĮæľĽ
    0.05
    æĿĥ
    0.05
    abouts
    0.05
     downside
    0.05
     Radi
    0.05
    Activations Density 0.009%

    No Known Activations