© 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. 35461
    Prev
    Next
    INDEX
    Explanations

    abbey, monastery, church

    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
    æĭ¾
    -0.09
    河西
    -0.09
     Healthy
    -0.09
    lexical
    -0.09
    urai
    -0.08
    unger
    -0.08
    éĥģ
    -0.08
    çĥŃçĪ±
    -0.08
    éĢıæĺİ
    -0.08
     Parks
    -0.08
    POSITIVE LOGITS
     Reco
    0.09
    æĢ»éĥ¨
    0.09
    å§Ĭ妹
    0.08
    çİ°éĩijæµģ
    0.08
    建çŃijçī©
    0.08
    æ£Ħ
    0.08
    çİ°åŃĺ
    0.08
    å®īç½®
    0.08
    åįĥåħĥ
    0.08
    å¼ĥ
    0.08
    Activations Density 0.110%

    No Known Activations