© 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. 32347
    Prev
    Next
    INDEX
    Explanations

    avoid + something

    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¦ģä¹Ī
    -0.11
    æĤī
    -0.10
    åIJ¬å®Į
    -0.09
    ä¸įæľį
    -0.09
    ä¸įåı¯éģ¿åħį
    -0.09
    æ¤Ł
    -0.09
    ahren
    -0.09
    arters
    -0.09
    åIJ¬çĿĢ
    -0.09
    fty
    -0.09
    POSITIVE LOGITS
    çļĦå°±æĺ¯
    0.10
    ä»»ä½ķå½¢å¼ı
    0.10
    theless
    0.10
    çĥĪ
    0.10
     ÑģилÑĮно
    0.09
    æľªæĪIJ
    0.08
    æĬĬä»ĸ
    0.08
     jug
    0.08
    éĤ£äºĽ
    0.08
    对ä»ĸ
    0.08
    Activations Density 0.023%

    No Known Activations