© 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. 35250
    Prev
    Next
    INDEX
    Explanations

    critical fails, miss chance, combos, attacks

    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
    ä¸ĢåŃĹ
    -0.10
    çĮ·
    -0.10
    çĪ¸çĪ¸
    -0.09
    åѦ龸
    -0.08
    åѦåīį
    -0.08
    åħĦ
    -0.08
    代è¨Ģ
    -0.08
    é«ĺåİŁ
    -0.08
    æĹĭ
    -0.08
    åĬ©çIJĨ
    -0.08
    POSITIVE LOGITS
    è¿ĩåİ»çļĦ
    0.10
    éĽĢ
    0.09
    incoming
    0.09
     бил
    0.09
    æĻĤãģ®
    0.09
    æĪIJåĬŁçļĦ
    0.08
    å¯Ĥ
    0.08
    æŀĩ
    0.08
    æĪIJåĬŁ
    0.08
    лÑĭ
    0.08
    Activations Density 0.042%

    No Known Activations