© 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. 30335
    Prev
    Next
    INDEX
    Explanations

    help, support, keep, guide

    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
    æĭħ
    -0.09
    atten
    -0.08
    墩
    -0.08
    å¾Ĺä¸įåĪ°
    -0.08
    æľīç§į
    -0.08
    رÙĤ
    -0.08
    TPL
    -0.08
    çĬ¶åħĥ
    -0.08
    解åĨ³éĹ®é¢ĺ
    -0.08
    tap
    -0.08
    POSITIVE LOGITS
    帮åĬ©
    0.30
     help
    0.28
    幫åĬ©
    0.26
     helps
    0.25
    help
    0.24
    帮å¿Ļ
    0.24
    帮
    0.24
    Help
    0.22
     helping
    0.22
    帮åĬ©ä¼ģä¸ļ
    0.22
    Activations Density 0.070%

    No Known Activations