© 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. 7419
    Prev
    Next
    INDEX
    Explanations

    counties and towns in England

    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
    åħļå·¥å§Ķ
    -0.10
    ä¸įèµ·
    -0.09
    bon
    -0.09
    éĵ²
    -0.09
     eventual
    -0.08
     bon
    -0.08
    å½ĵä¹ĭ
    -0.08
    åĿŀ
    -0.08
    以åıĬåħ¶ä»ĸ
    -0.08
    esta
    -0.08
    POSITIVE LOGITS
    çĭŃ
    0.11
    çĭ
    0.10
    èĹī
    0.09
    iana
    0.09
    imiter
    0.09
    shire
    0.09
    ä»Ģä¹Īåij¢
    0.08
    rist
    0.08
    æĢ§çļĦ
    0.08
    åĪ¶åº¦æĶ¹éĿ©
    0.08
    Activations Density 0.037%

    No Known Activations