© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9792
    Prev
    Next
    INDEX
    Explanations

    sorghum, maize, flowers, oil

    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
    åĪ«çļĦ
    -0.10
    è¹Ģ
    -0.10
    泡
    -0.09
    èĢħçļĦ
    -0.09
    åĺĮ
    -0.09
    ä¸ĭæ²ī
    -0.09
    \Collections
    -0.08
    éĥ¢
    -0.08
    æĻķ
    -0.08
    æŁľ
    -0.08
    POSITIVE LOGITS
    ç±½
    0.10
    åĶ®åIJİ
    0.10
    iani
    0.09
     Drum
    0.09
     drum
    0.09
    apos
    0.09
    uer
    0.08
    arium
    0.08
    grams
    0.08
     palms
    0.08
    Activations Density 0.004%

    No Known Activations