© 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. 63166
    Prev
    Next
    INDEX
    Explanations

    genetic diversity and breeding

    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
    èĥĿ
    -0.10
    åį°
    -0.10
    pone
    -0.09
    atz
    -0.09
    æ¼ı
    -0.09
    çļĦåĬ¨ä½ľ
    -0.09
    çļĦåİĭåĬĽ
    -0.09
     íļ
    -0.09
    åģı好
    -0.09
    ripp
    -0.08
    POSITIVE LOGITS
    æ´»åĬĽ
    0.21
    çĶŁåij½åĬĽ
    0.18
    çĶŁæľº
    0.14
     vigor
    0.14
     vig
    0.14
     vitality
    0.12
    åĭĥåĭĥ
    0.12
    vig
    0.11
    çĶŁåij½
    0.11
    æĪĺæĸĹåĬĽ
    0.11
    Activations Density 0.051%

    No Known Activations