© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51475
    Prev
    Next
    INDEX
    Explanations

    Safari browser

    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
    æĦŁ
    -0.11
    ht
    -0.10
    ration
    -0.10
    åħľ
    -0.09
    åı£è¢ĭ
    -0.09
    åı¦ä¸ĢåįĬ
    -0.09
    hest
    -0.09
    åįĸæİī
    -0.09
    croll
    -0.09
    åĽ½å®¶å®īåħ¨
    -0.09
    POSITIVE LOGITS
    åİ
    0.10
    (bc
    0.09
    jis
    0.08
    unas
    0.08
    ometers
    0.08
     Cru
    0.08
    æĺ¶
    0.08
    alon
    0.08
     Synopsis
    0.08
    idas
    0.08
    Activations Density 0.050%

    No Known Activations