© 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. 21488
    Prev
    Next
    INDEX
    Explanations

    laser, ship, goji berry, easter

    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
     mashed
    -0.05
     voulais
    -0.05
    หà¸Ļ
    -0.05
     witnessing
    -0.05
    ?
    -0.05
    иÑı
    -0.05
    åĩºä¸į
    -0.05
    ò
    -0.05
     destiny
    -0.05
    älla
    -0.05
    POSITIVE LOGITS
    èģĶ
    0.07
    èģ¯
    0.06
    ables
    0.06
    许åı¯æĸĩ件
    0.06
     Heat
    0.06
    anship
    0.06
    ä¹ĭ乡
    0.06
    æĹłå¿§
    0.05
    ecat
    0.05
    eturn
    0.05
    Activations Density 0.067%

    No Known Activations