© 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. 20603
    Prev
    Next
    INDEX
    Explanations

    choose or can

    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
    æĸ°å¸¸æĢģ
    -0.06
    ta
    -0.06
    oka
    -0.06
    :X
    -0.05
    ç§ijæĬĢåѦéĻ¢
    -0.05
     ta
    -0.05
     actief
    -0.05
    %@
    -0.05
    ä¸ĢçĽ´ä»¥
    -0.05
    кнÑĥ
    -0.05
    POSITIVE LOGITS
    æ¸ħæĸ°
    0.06
    å¿ĺ
    0.05
    oft
    0.05
    åĪĨãģij
    0.05
    åľ°çĤ¹
    0.05
    ç»Ħç»ĩé¢Ĩ导
    0.05
    isional
    0.05
     Correct
    0.05
    onu
    0.05
    æĽ
    0.05
    Activations Density 0.002%

    No Known Activations