© 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. 53495
    Prev
    Next
    INDEX
    Explanations

    numbers and specific dates

    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
    è¿Ļæł·æīįèĥ½
    -0.10
     etc
    -0.08
    âĢ¦âĢ¦
    -0.08
    以æѤ
    -0.08
    èĥ½èĢĹ
    -0.08
    åĺĽ
    -0.08
     ÑĢей
    -0.08
    ä½ľä¸ºä¸Ģ个
    -0.08
    abl
    -0.07
    çŃīéĹ®é¢ĺ
    -0.07
    POSITIVE LOGITS
    åIJĮæł·æĺ¯
    0.10
    ãģĵãģ¡ãĤī
    0.09
    orp
    0.08
    onders
    0.08
    æľĢ好æĺ¯
    0.08
    Ø£Ùĩد
    0.08
    å½ĵä¹ĭæĹłæĦ§
    0.08
    ä¸ĭä¸Ģç¯ĩ
    0.08
    ibold
    0.08
    exels
    0.08
    Activations Density 0.210%

    No Known Activations