© 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. 10963
    Prev
    Next
    INDEX
    Explanations

    melon, cantaloupe, watermelon, gourd types

    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
    æīĵåĩ»
    -0.09
    åĩ¶
    -0.09
    亮
    -0.09
    èį¼
    -0.09
    fitness
    -0.08
    亢
    -0.08
    itant
    -0.08
    æĸĵ
    -0.08
     shoe
    -0.08
     Fro
    -0.08
    POSITIVE LOGITS
    ðŁįī
    0.11
    ç±½
    0.09
    atum
    0.09
    å®ŀ践活åĬ¨
    0.09
    绶
    0.09
    inals
    0.09
    å±±åºĦ
    0.09
    quist
    0.09
    èĩ¬
    0.09
    pek
    0.09
    Activations Density 0.007%

    No Known Activations