© 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. 20453
    Prev
    Next
    INDEX
    Explanations

    to followed by verb

    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
    è¾ĥ
    -0.09
     Donovan
    -0.09
    æī¿
    -0.09
    .paging
    -0.09
    æĪijèĥ½
    -0.09
    å®ĥæĺ¯
    -0.09
    çĤ¹å¤ļ
    -0.09
    å®ĮæĪIJäºĨ
    -0.09
    Ãłng
    -0.08
    çĹħæ¯ĴæĦŁæŁĵ
    -0.08
    POSITIVE LOGITS
    å¥İ
    0.11
    åħ®
    0.10
    ä¼ļæľī
    0.09
    waÅĤ
    0.09
    éĻĨç»Ń
    0.09
    çļĦå°±æĺ¯
    0.09
    ä¹Łä¼ļ
    0.09
    imiento
    0.08
    åģķ
    0.08
     pil
    0.08
    Activations Density 0.073%

    No Known Activations