© 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. 18447
    Prev
    Next
    INDEX
    Explanations

    ends of lines/concepts

    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
    ypes
    -0.06
    ubes
    -0.06
    us
    -0.06
     sao
    -0.06
    abia
    -0.05
    onne
    -0.05
    URES
    -0.05
    umes
    -0.05
     us
    -0.05
    stit
    -0.05
    POSITIVE LOGITS
    强
    0.06
    enho
    0.06
    ä¸Ģåıį
    0.06
    çľ¼çľĭ
    0.05
    åij½ä¸Ń
    0.05
    mêmes
    0.05
    å¼·
    0.05
    SR
    0.05
    esto
    0.05
    ectu
    0.05
    Activations Density 0.104%

    No Known Activations