© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21908
    Prev
    Next
    INDEX
    Explanations

    kitchen, appliance, sink

    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
    楮
    -0.10
    è¢ĭ
    -0.10
    è¿Ļæīįæĺ¯
    -0.10
    azy
    -0.09
    (visitor
    -0.09
    ÑĤÑı
    -0.09
    åİ»è¿ĩ
    -0.09
    éºĴ
    -0.09
    ä¼ļéķ¿
    -0.09
    EDIUM
    -0.09
    POSITIVE LOGITS
    æ´Ĺè¡£æľº
    0.12
    马桶
    0.11
    åį«çĶŁéĹ´
    0.11
     kitchen
    0.11
    æ´Ĺ涤
    0.11
    åĨ°ç®±
    0.11
    çģ¶
    0.11
    ãĤŃãĥĥãĥģãĥ³
    0.10
     Kitchen
    0.10
    sink
    0.10
    Activations Density 0.157%

    No Known Activations