© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19573
    Prev
    Next
    INDEX
    Explanations

    "i heard a piper piping"

    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
    çIJĨåĮĸ
    -0.06
    elev
    -0.06
    ARAM
    -0.06
    posit
    -0.06
    涤
    -0.06
    variant
    -0.06
    statt
    -0.06
    ä¸į移
    -0.06
    ä¸įæĹ©
    -0.05
    æĹ·
    -0.05
    POSITIVE LOGITS
    aine
    0.05
    å¿į
    0.05
     ‘
    0.05
    ain
    0.05
    aksimalkan
    0.05
     sum
    0.05
     Earn
    0.05
    å®īåħ¨çĽij管
    0.05
     skirts
    0.05
    ampo
    0.05
    Activations Density 0.001%

    No Known Activations