© 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. 8188
    Prev
    Next
    INDEX
    Explanations

    crystal axes and structure

    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
    filer
    -0.10
    ghi
    -0.09
     Peripheral
    -0.08
    åħ¥åħļ
    -0.08
    æ¼Ĩ
    -0.08
     Revel
    -0.08
    å¼Ģåı£
    -0.08
    å¸ı
    -0.08
    å¨ģæħij
    -0.08
    adoo
    -0.08
    POSITIVE LOGITS
    纶
    0.09
    磬
    0.09
    头èĦij
    0.09
     Wäh
    0.09
    ä¼łéĶĢ
    0.09
    redd
    0.09
     Indo
    0.09
    èľĥ
    0.09
     unary
    0.09
    ULE
    0.09
    Activations Density 0.075%

    No Known Activations