© 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. 34385
    Prev
    Next
    INDEX
    Explanations

    programs begin offering

    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¤įå·¥
    -0.11
    åħ¬çĽĬ
    -0.09
    styl
    -0.08
    çĶŁäº§çĶŁæ´»
    -0.08
    åĽ´
    -0.08
    å³
    -0.08
    ssf
    -0.08
    avy
    -0.08
    å°ģ
    -0.08
    æµ·åºķ
    -0.08
    POSITIVE LOGITS
    åĬŀåѦ
    0.16
    æĭĽçĶŁ
    0.12
    å¼Ģ设
    0.12
     courses
    0.11
    æĭĽæĶ¶
    0.11
     programs
    0.11
     Programs
    0.11
    人æīįåŁ¹åħ»
    0.10
    çī¹èī²
    0.10
    æ¯ıå¹´éĥ½
    0.10
    Activations Density 0.106%

    No Known Activations