© 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. 17922
    Prev
    Next
    INDEX
    Explanations

    constructor and initialization

    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
    anford
    -0.06
    ç¥
    -0.06
    handel
    -0.06
    idden
    -0.06
    ãĤ¿ãĥ«
    -0.05
    entifier
    -0.05
     Posted
    -0.05
    itten
    -0.05
    æģ°åĪ°
    -0.05
    ì§Ħ
    -0.05
    POSITIVE LOGITS
     pit
    0.06
    æķĻèĤ²äºĭä¸ļ
    0.05
    à¸ĺรรม
    0.05
    åľ¨æī§è¡Į
    0.05
     Sommer
    0.05
    å½±
    0.05
    رÙĪض
    0.05
     air
    0.05
    ulu
    0.05
    ÙĪØ«
    0.05
    Activations Density 0.001%

    No Known Activations