© 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. 36958
    Prev
    Next
    INDEX
    Explanations

    AFL, Heart, Media

    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
    管家
    -0.08
    ноÑģ
    -0.08
    rops
    -0.08
    _pull
    -0.08
    ely
    -0.08
    noc
    -0.08
    以åıĬåħ¶ä»ĸ
    -0.08
    æ¡İ
    -0.08
    çŃĿ
    -0.08
    åĶ®
    -0.07
    POSITIVE LOGITS
    æĭĹ
    0.11
    åħļé£İ
    0.09
    åĪ«äººçļĦ
    0.09
    á»Ŀ
    0.09
    ]int
    0.09
    é¼ł
    0.09
    çģ«çĥ§
    0.09
     ÐĹна
    0.09
    кÑĤ
    0.09
    ç»
    0.09
    Activations Density 0.003%

    No Known Activations