© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 9471
    Prev
    Next
    INDEX
    Explanations

    future, forthcoming, -old

    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
    åħ¨çľģ
    -0.08
    .scalar
    -0.08
    没æľī人
    -0.08
    å°ı康
    -0.08
    åºł
    -0.08
    æĺ¯æ¯Ķè¾ĥ
    -0.08
     POV
    -0.08
    itra
    -0.08
     Brenda
    -0.08
    æľīçļĦ人
    -0.08
    POSITIVE LOGITS
    éĺ¶æ®µæĢ§
    0.09
    <![
    0.09
     famously
    0.09
    ont
    0.09
    åĩĿ
    0.09
     Pandora
    0.09
    æĬĦ
    0.08
    à¸ķำ
    0.08
    伸åĩº
    0.08
    çĹĶ
    0.08
    Activations Density 0.081%

    No Known Activations