© 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. 16699
    Prev
    Next
    INDEX
    Explanations

    CB Hornet

    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
    uss
    -0.10
    è··
    -0.09
    èŁ²
    -0.08
    åĬĽè¿ĺæĺ¯
    -0.08
    è¯Ļ
    -0.08
    综
    -0.08
    佯
    -0.08
    à¸Ħà¸ĵะ
    -0.08
    æĹİ
    -0.08
    ì¹¼
    -0.08
    POSITIVE LOGITS
    åŁºæľ¬éĿ¢
    0.10
    éļ¼
    0.10
    leta
    0.09
    سÙĪر
    0.09
    è¾ĩ
    0.09
    éĿ¢çĽ®
    0.08
    valu
    0.08
    æĿ¾
    0.08
    åīįåĪĹ
    0.08
    iden
    0.08
    Activations Density 0.014%

    No Known Activations