© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    by + noun

    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
    èģĶç½ij
    -0.09
    éľĦ
    -0.09
    è¸ŀ
    -0.08
    è§ģæķĪ
    -0.08
     Siri
    -0.08
    éļħ
    -0.08
     proc
    -0.08
     manip
    -0.07
    åĶ¾
    -0.07
    stars
    -0.07
    POSITIVE LOGITS
    åģľæĶ¾
    0.10
    çĶŁæ´»çݯå¢ĥ
    0.10
    æīĭåĬ¿
    0.09
    serter
    0.09
     sheer
    0.09
     virtue
    0.09
    puty
    0.09
    illion
    0.09
    enville
    0.09
    wner
    0.09
    Activations Density 0.042%

    No Known Activations