© 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. 8275
    Prev
    Next
    INDEX
    Explanations

    B cell lymphoma types

    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
    vr
    -0.09
    èĥľ
    -0.09
    ãģķãģĦ
    -0.09
    人次
    -0.09
    èĤļåŃIJ
    -0.09
    äºĮæ°§åĮĸ碳
    -0.08
    æĸ°åĮº
    -0.08
    åĨ¶éĩij
    -0.08
    寸
    -0.08
     Dahl
    -0.08
    POSITIVE LOGITS
    æĮŁ
    0.09
    æĥĨ
    0.09
    çĶ¥
    0.09
    Touches
    0.08
    èħķ
    0.08
    è¦ģç´§
    0.08
    drops
    0.08
    FO
    0.08
    æį»
    0.08
    chal
    0.08
    Activations Density 0.490%

    No Known Activations