© 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. 21282
    Prev
    Next
    INDEX
    Explanations

    de followed by names or .f/.v

    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
    /or
    -0.11
    åİ¥
    -0.09
    sWith
    -0.09
    ãģĵãģ¨
    -0.08
    det
    -0.08
    do
    -0.08
    gram
    -0.08
    gerald
    -0.08
    ioni
    -0.08
    ä¸ļæĢģ
    -0.08
    POSITIVE LOGITS
    acon
    0.10
    velopment
    0.10
    formed
    0.10
    ends
    0.10
    PEND
    0.10
    aos
    0.09
    veloper
    0.09
    ffer
    0.09
    æĸĩåĮĸåĴĮ
    0.09
    roit
    0.09
    Activations Density 0.064%

    No Known Activations