© 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. 39947
    Prev
    Next
    INDEX
    Explanations

    developed by

    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
    1
    -0.08
    驳
    -0.08
     negativity
    -0.08
     bef
    -0.08
    0
    -0.08
     prospect
    -0.08
    8
    -0.07
    墩
    -0.07
    追踪
    -0.07
    ason
    -0.07
    POSITIVE LOGITS
    åĽ¢éĺŁ
    0.15
    å¹ķåIJİ
    0.13
    æĬĢæľ¯çłĶåıij
    0.13
    çłĶåıij
    0.12
    åľĺéļĬ
    0.12
    å¼ĢåıijèĢħ
    0.11
     team
    0.11
    å¼Ģåıij
    0.11
    åıijæĺİ
    0.11
    team
    0.11
    Activations Density 0.416%

    No Known Activations