© 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. 4647
    Prev
    Next
    INDEX
    Explanations

    at some point or time

    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
    æĬķ
    -0.10
    æĢķ
    -0.09
    argest
    -0.08
     matters
    -0.08
     NOM
    -0.08
     relaxation
    -0.08
    igor
    -0.08
    matter
    -0.07
    erald
    -0.07
     Typ
    -0.07
    POSITIVE LOGITS
    è¡Įä¸ļåĨħ
    0.10
    侯
    0.10
    å¸Ĥåľºä»·æł¼
    0.10
    èĥĥèĤł
    0.09
    人çĶŁçļĦ
    0.09
    çĸ¾çĹħçļĦ
    0.09
    æĪijæĬĬ
    0.09
    ADX
    0.09
    宿
    0.09
    åĸĦæĦı
    0.09
    Activations Density 0.026%

    No Known Activations