© 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. 26196
    Prev
    Next
    INDEX
    Explanations

    cables and connectors

    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
    undy
    -0.09
    çģµæĦŁ
    -0.09
    亲è¿ij
    -0.08
    èĩ´æķ¬
    -0.08
    æĪijæĥ³
    -0.08
    achel
    -0.08
    å®ļæŶ
    -0.08
    hardt
    -0.08
    è·ŁæĪij
    -0.08
    _IMPL
    -0.08
    POSITIVE LOGITS
    æĿµ
    0.11
    .openConnection
    0.09
     connector
    0.09
    å¥Ĺè·¯
    0.09
    å©
    0.09
    çĶµç¼Ĩ
    0.09
    éĿ¢æĿ¿
    0.09
    è¡°
    0.09
    ä¼łè¾ĵ
    0.09
     cables
    0.09
    Activations Density 0.142%

    No Known Activations