© 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. 21145
    Prev
    Next
    INDEX
    Explanations

    paid or free options

    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
    rote
    -0.10
    ä½ĵéĩı
    -0.10
     пÑĢог
    -0.09
    èĵĭ
    -0.09
    大夫
    -0.09
    SAME
    -0.09
    æħij
    -0.09
    æľį
    -0.09
    istan
    -0.09
     Gast
    -0.09
    POSITIVE LOGITS
    ä»ĺè´¹
    0.26
    æĶ¶è´¹
    0.20
    æĶ¶è²»
    0.16
    æĹłåģ¿
    0.16
    åħįè´¹
    0.16
     paid
    0.15
    Paid
    0.15
    paid
    0.14
     Paid
    0.14
    代价
    0.14
    Activations Density 0.120%

    No Known Activations