© 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. 21078
    Prev
    Next
    INDEX
    Explanations

    echoing

    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
    侧
    -0.06
     ther
    -0.06
    verter
    -0.06
    约
    -0.06
    è¿ĩ
    -0.05
     over
    -0.05
    éĶĢ
    -0.05
    аÑĩ
    -0.05
    à·Ĵනà·Ĭ
    -0.05
     unt
    -0.05
    POSITIVE LOGITS
    å·¡è§Ĩåijĺ
    0.07
    ä¸İç»´æĬ¤
    0.07
    çļĦéĥ½
    0.06
    anton
    0.06
    éĢıåħī
    0.06
    пÑĤа
    0.06
    ä¸İåİŁ
    0.06
    ä¸İåīį
    0.06
    åĴĮä¸ī
    0.06
    移åĬ¨å¼ı
    0.06
    Activations Density 0.020%

    No Known Activations