© 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. 3645
    Prev
    Next
    INDEX
    Explanations

    testing and evaluation

    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
    .shtml
    -0.09
    æľīæĿĥ
    -0.09
    ä¸įåı¯éģ¿åħį
    -0.09
    ence
    -0.08
    ç»ĵå°¾
    -0.08
    纳ç¨İ
    -0.08
    æѤæĸĩ
    -0.08
    åīį端
    -0.08
    Submitting
    -0.08
    imit
    -0.08
    POSITIVE LOGITS
    æµĭè¯ķ
    0.10
    åijĬ
    0.09
     tests
    0.09
     performance
    0.09
    æĢ§èĥ½
    0.09
    äºĨä¸Ģç³»åĪĹ
    0.09
     conducted
    0.09
    äºĨä¸Ģåľº
    0.09
    稳å®ļæĢ§
    0.09
    æĴķ
    0.09
    Activations Density 0.236%

    No Known Activations