© 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. 53801
    Prev
    Next
    INDEX
    Explanations

    also a creator or role

    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
    å°Ķ
    -0.11
    仪
    -0.10
    owe
    -0.10
    hcp
    -0.09
    缺ä¹ı
    -0.09
    衬
    -0.09
    çĪ¾
    -0.08
    alysis
    -0.08
    èIJİ
    -0.08
    ervo
    -0.08
    POSITIVE LOGITS
    åħ¼èģĮ
    0.11
    åĪ«çļĦ
    0.10
    åħ¼ä»»
    0.10
     roles
    0.09
     ÑģÑĦ
    0.09
     moon
    0.09
     nightly
    0.09
    åħ³åĪĩ
    0.08
    åħ¼
    0.08
    å½¹
    0.08
    Activations Density 0.091%

    No Known Activations