© 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. 2385
    Prev
    Next
    INDEX
    Explanations

    enlighten or enlightenment

    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
    illos
    -0.10
    ä»Ģä¹Īéĥ½
    -0.09
    nette
    -0.09
    ortion
    -0.09
    unks
    -0.09
    ±
    -0.09
    yles
    -0.09
    è¸
    -0.08
     bụng
    -0.08
    osal
    -0.08
    POSITIVE LOGITS
    æĽĻåħī
    0.11
    æĻ°
    0.11
    åīĤ
    0.10
    enment
    0.10
    uru
    0.09
    ilde
    0.09
    éĨIJ
    0.09
     ÑĤомÑĥ
    0.09
    åįģ足
    0.09
    女ç¥ŀ
    0.09
    Activations Density 0.011%

    No Known Activations