© 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. 9164
    Prev
    Next
    INDEX
    Explanations

    mobile app, SDK, Web, name

    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
    绶
    -0.08
    ance
    -0.08
     record
    -0.08
    educ
    -0.08
     desk
    -0.08
    ê¸ī
    -0.08
    âĢ¾
    -0.07
    èĶĵ
    -0.07
    desk
    -0.07
    enk
    -0.07
    POSITIVE LOGITS
    atica
    0.10
    çľĭçĹħ
    0.10
    éĢĥèĦ±
    0.10
    åĩºåİĤ
    0.10
    ç¬Ĩ
    0.10
    ç¾İæĸ¹
    0.09
    åħ¨é¢Ŀ
    0.09
    漪
    0.09
    åŃ¦ä¹łæĪIJ绩
    0.09
    æ³Ķ
    0.09
    Activations Density 0.011%

    No Known Activations