© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 27932
    Prev
    Next
    INDEX
    Explanations

    names after articles/titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    ç¬Ħ
    -0.10
    çĽĶ
    -0.09
    åIJij社ä¼ļ
    -0.09
    å®Ļ
    -0.09
    åºĨ幸
    -0.09
    oyo
    -0.09
    éħª
    -0.09
    å²Ń
    -0.09
    å±Ĭæ¯ķä¸ļçĶŁ
    -0.09
    åĪĽæĸ°åŀĭ
    -0.08
    POSITIVE LOGITS
     дела
    0.08
    ç¼ł
    0.08
    æĭĽèģĺ
    0.08
    à¤ĭ
    0.08
    åĤħ
    0.08
    ÐIJÐĿ
    0.08
    аÑĢÑĮ
    0.08
     микÑĢо
    0.08
     automatic
    0.08
    è¯Ń
    0.08
    Activations Density 0.023%

    No Known Activations