© 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. 22037
    Prev
    Next
    INDEX
    Explanations

    "laugh test"

    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
    æķĪ
    -0.06
    edia
    -0.06
    溯
    -0.05
    ÑĤаки
    -0.05
    趣
    -0.05
    pecified
    -0.05
     le
    -0.05
    aktan
    -0.05
    à¸Ĺรà¸ĩ
    -0.05
    ä¼ł
    -0.05
    POSITIVE LOGITS
    亢
    0.05
    ä¸Ĭæŀ¶
    0.05
    punk
    0.05
    licht
    0.05
    çļĦæīĭæ³ķ
    0.05
    wil
    0.05
    rees
    0.05
    lech
    0.05
    为è°ģ
    0.05
    tet
    0.05
    Activations Density 0.007%

    No Known Activations