© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9043
    Prev
    Next
    INDEX
    Explanations

    filing or report with results

    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
    lei
    -0.10
    ä¿Ŀä½ı
    -0.10
    kit
    -0.08
    вед
    -0.08
    éĽĨä¸Ń
    -0.08
    åĩºåħ¥
    -0.08
    .fp
    -0.07
    _CRE
    -0.07
    说åĩº
    -0.07
    lene
    -0.07
    POSITIVE LOGITS
    åħ¶ä¸ŃåĮħæĭ¬
    0.09
     bitten
    0.09
    çijŀ士
    0.09
    æĥķ
    0.09
    çĬ
    0.08
    åĮºåŁŁåĨħ
    0.08
    èĢģå©Ĩ
    0.08
    èIJį
    0.08
    rans
    0.08
    磼
    0.08
    Activations Density 0.013%

    No Known Activations