© 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. 36190
    Prev
    Next
    INDEX
    Explanations

    featherweight title

    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
     rebate
    -0.09
     reb
    -0.09
    æ¬ł
    -0.09
    åIJİæİĴ
    -0.09
    åIJĦåİ¿
    -0.09
    FIG
    -0.09
    bao
    -0.08
    âĩĵ
    -0.08
    emann
    -0.08
     BAT
    -0.08
    POSITIVE LOGITS
    æĹºçĽĽ
    0.10
    ook
    0.10
    ookies
    0.09
    ä¹ĭäºī
    0.09
    quier
    0.09
    ookie
    0.08
    éĹ´çļĦ
    0.08
    级åĪ«çļĦ
    0.08
    ãĤį
    0.08
    货车
    0.08
    Activations Density 0.012%

    No Known Activations