© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 52104
    Prev
    Next
    INDEX
    Explanations

    findings

    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
     Ñģобой
    -0.10
    listed
    -0.09
    liness
    -0.09
    祢
    -0.09
    prov
    -0.08
    osal
    -0.08
    æĩĤ
    -0.08
    ä¹Ŀæ±Ł
    -0.08
    åѦéĹ®
    -0.08
    pie
    -0.08
    POSITIVE LOGITS
    åĻİ
    0.11
    ucs
    0.10
    fter
    0.08
    re
    0.08
    è¾ĸåĮº
    0.08
    åıªè¦ģæĺ¯
    0.08
    æĬ¥åijĬ
    0.08
    ç»ĵ论
    0.08
    /results
    0.08
    atre
    0.08
    Activations Density 0.028%

    No Known Activations