© 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. 16523
    Prev
    Next
    INDEX
    Explanations

    mining

    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
    æĻĴ
    -0.09
    æĥł
    -0.09
    çĦIJ
    -0.08
    _Event
    -0.08
    è¾½
    -0.08
    åĨľæĿij
    -0.08
    _secure
    -0.08
     Nurs
    -0.08
    ä¸Ģéģį
    -0.08
    èĢ»
    -0.08
    POSITIVE LOGITS
    å¼Ģéĩĩ
    0.12
    çŁ¿ä¸ļ
    0.11
    éĩĩçŁ¿
    0.10
    lements
    0.10
     miners
    0.09
    éĻ¢åī¯éĻ¢éķ¿
    0.09
     mining
    0.09
    aldi
    0.09
    æīĵåĩ»
    0.09
     miner
    0.08
    Activations Density 0.076%

    No Known Activations