© 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. 19789
    Prev
    Next
    INDEX
    Explanations

    buy, download, get

    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
    deen
    -0.08
    imity
    -0.07
    arity
    -0.07
    åıĪéģĵ
    -0.07
    ikel
    -0.07
    eldes
    -0.06
    kow
    -0.06
    evity
    -0.06
    é¦į
    -0.06
    æĤ¨çļĦè¯Ħ论
    -0.06
    POSITIVE LOGITS
    触
    0.05
    urs
    0.05
    --
    0.05
    对
    0.05
    ++
    0.05
     unde
    0.05
     major
    0.05
    åĽŀ
    0.04
    c
    0.04
    3
    0.04
    Activations Density 0.016%

    No Known Activations