© 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. 21161
    Prev
    Next
    INDEX
    Explanations

    go/goes/came into

    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
    ta
    -0.07
    ÙĦا
    -0.06
    itasi
    -0.05
    éĹ²
    -0.05
    combination
    -0.05
    ä¸ĩåħĥå·¦åı³
    -0.05
    chetta
    -0.05
    欢
    -0.05
    genre
    -0.05
    la
    -0.05
    POSITIVE LOGITS
    awang
    0.05
    воÑİ
    0.05
    èªįå®ļ
    0.05
    åıĪéģĵ
    0.05
    以éĻį
    0.05
    åĴĮä¸ĸçķĮ
    0.05
    uchu
    0.05
     impact
    0.05
    apo
    0.05
    éĻIJãĤĬ
    0.05
    Activations Density 0.001%

    No Known Activations