© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7131
    Prev
    Next
    INDEX
    Explanations

    .patch files

    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
    IRD
    -0.10
    AMI
    -0.09
    .running
    -0.09
    çĻ½éĵ¶
    -0.09
    æİĺ
    -0.09
    åĩ«
    -0.09
    idding
    -0.08
    ilda
    -0.08
    ibs
    -0.08
    ราà¸Ĭà¸ģาร
    -0.08
    POSITIVE LOGITS
     PATCH
    0.09
    acie
    0.09
    å¤ļåħĥåĮĸ
    0.09
    å¼ĢæĿ¥
    0.09
    åIJĮæľŁ
    0.08
    çŁ¥éģĵäºĨ
    0.08
    èĩªæĦ¿
    0.08
    .patch
    0.08
    å°ijä¸įäºĨ
    0.08
    估计
    0.08
    Activations Density 0.005%

    No Known Activations