© 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. 19848
    Prev
    Next
    INDEX
    Explanations

    here to

    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
    ç§Ģ
    -0.06
    -0.05
    ม
    -0.05
    ously
    -0.05
    t
    -0.05
    åı¯ä¾Ľ
    -0.05
     nun
    -0.05
    (
    -0.05
    !
    -0.05
    æĵį
    -0.05
    POSITIVE LOGITS
    ayang
    0.08
    itse
    0.08
    ersatz
    0.07
    å®ŀæĻ¯åĽ¾
    0.07
    olie
    0.06
    زÙĬز
    0.06
     truc
    0.06
    meden
    0.06
    llx
    0.06
    asanya
    0.06
    Activations Density 0.001%

    No Known Activations