© 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. 20846
    Prev
    Next
    INDEX
    Explanations

    months, days, or specific events

    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
    ughter
    -0.05
    çļĦåħ¨
    -0.05
    oom
    -0.05
    licer
    -0.05
    漪
    -0.05
    esian
    -0.05
    sir
    -0.05
    士
    -0.04
    CELL
    -0.04
    iren
    -0.04
    POSITIVE LOGITS
    éĢģä¸Ģ
    0.07
    åĩłåįģ个
    0.06
    çĻ¾è®¡
    0.06
    ä¸Ńãģ§ãģĻ
    0.06
     garantiz
    0.06
    å¾Īå¤ļåľ°æĸ¹
    0.06
    coce
    0.06
    à¹Ĥà¸ķ
    0.06
    деÑı
    0.06
    onis
    0.06
    Activations Density 0.001%

    No Known Activations