© 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. 55484
    Prev
    Next
    INDEX
    Explanations

    treated or violated

    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
    emento
    -0.09
    ä»İ容
    -0.08
    åħĭæľį
    -0.08
    æĬµæĬĹ
    -0.08
    è±ĩ
    -0.08
    çļĦä¼ĺåĬ¿
    -0.08
    çĤľ
    -0.08
     rem
    -0.08
    éĤ£ä½į
    -0.08
    åħĭæĭī
    -0.08
    POSITIVE LOGITS
    åį´è¢«
    0.13
    å¾Ĺä¸įåĪ°
    0.12
    就被
    0.11
    被
    0.10
    ä¸įåħ¬å¹³
    0.10
    жи
    0.09
    åIJĪæ³ķæĿĥçĽĬ
    0.09
    adic
    0.09
    éĥ½è¢«
    0.09
    æł¹æľ¬æ²¡æľī
    0.09
    Activations Density 0.283%

    No Known Activations