© 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. 34702
    Prev
    Next
    INDEX
    Explanations

    storage space and data capacity

    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
    综åIJĪç´łè´¨
    -0.10
    æ½ľ
    -0.09
     Pew
    -0.08
    æİ¥åĪ°
    -0.08
    æĩĴ
    -0.08
    æµĭè¯Ħ
    -0.08
     leth
    -0.08
    å¼Ħ
    -0.08
    鼷éĶĭ
    -0.08
    çļĦéĢŁåº¦
    -0.08
    POSITIVE LOGITS
    容éĩı
    0.11
    .storage
    0.11
    空éĹ´
    0.10
    åĨħåŃĺ
    0.10
    容
    0.10
    空éĸĵ
    0.10
     memory
    0.10
    è´®
    0.09
     space
    0.09
     storage
    0.09
    Activations Density 0.081%

    No Known Activations