© 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. 37922
    Prev
    Next
    INDEX
    Explanations

    this is

    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
    è£
    -0.09
    appa
    -0.08
    çļĦåĬŀæ³ķ
    -0.08
    è¿Ļæĺ¯åĽłä¸º
    -0.08
    çļĦåģļæ³ķ
    -0.08
    åĽ½èµĦ
    -0.08
    æŃ¤ä¸¾
    -0.08
    ãģĹãĤĥ
    -0.08
    寰
    -0.08
    纥
    -0.08
    POSITIVE LOGITS
    æĮij
    0.10
    笺
    0.10
    iec
    0.09
    åĮ£
    0.09
    èĬ½
    0.09
    æį»
    0.09
    pickle
    0.09
    íį¼
    0.09
    çĮ¿
    0.09
    ouce
    0.09
    Activations Density 0.029%

    No Known Activations