© 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. 17806
    Prev
    Next
    INDEX
    Explanations

    a or an followed by noun

    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
    &
    -0.06
    ertain
    -0.05
    ëĭ¤
    -0.05
    رÙĪز
    -0.05
    åı¯ä»¥
    -0.05
    -testing
    -0.05
    ÑģÑĤа
    -0.05
    代
    -0.05
    inian
    -0.05
    æĸ¹æ¡Ī
    -0.04
    POSITIVE LOGITS
    âĢ¦).
    0.07
    zem
    0.07
     {}).
    0.07
    ãģĹãĤį
    0.06
    âĢ¦*
    0.06
    为äºĨç»Ļ
    0.06
    âĢ¦),
    0.06
    aner
    0.06
     \`
    0.06
    为äºĨ让
    0.06
    Activations Density 0.029%

    No Known Activations