© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29518
    Prev
    Next
    INDEX
    Explanations

    earlier this

    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
    Negative Logits
    åħ·ä½ĵæĥħåĨµ
    -0.12
    mith
    -0.11
    tat
    -0.11
    ï¸
    -0.10
     riêng
    -0.10
    ably
    -0.10
    å±ĬæŶ
    -0.10
    缮åīįå·²
    -0.09
    åŁºæľ¬æĥħåĨµ
    -0.09
     currently
    -0.09
    POSITIVE LOGITS
    _THAN
    0.12
    -stage
    0.11
    _than
    0.11
    说è¿ĩ
    0.11
    -than
    0.11
    æĪij以为
    0.10
    Than
    0.10
    mente
    0.09
    輩
    0.09
    most
    0.09
    Activations Density 0.009%

    No Known Activations