© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33848
    Prev
    Next
    INDEX
    Explanations

    ledger or ledge

    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
    attery
    -0.09
    è¿ľæ´ĭ
    -0.09
     же
    -0.08
     mainland
    -0.08
     Derrick
    -0.08
    åĪŃ
    -0.08
    åķī
    -0.08
     ÑĢабоÑĤе
    -0.08
    è½¬åŁºåĽł
    -0.08
    ores
    -0.08
    POSITIVE LOGITS
    æѤäºĭ
    0.10
    人å¿ĥ
    0.10
    åijĺ
    0.10
    hog
    0.10
    eder
    0.09
    好æ¶Īæģ¯
    0.09
    æĺı
    0.09
    æĹģ
    0.09
    ä»Ģä¹ĪåİŁåĽł
    0.09
    mal
    0.09
    Activations Density 0.004%

    No Known Activations