© 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. 23634
    Prev
    Next
    INDEX
    Explanations

    actor names

    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
    欹
    -0.10
    èħ°éĥ¨
    -0.09
    çľĭçĶµè§Ĩ
    -0.08
    ç»ŀ
    -0.08
    械
    -0.08
    èĻĶ
    -0.08
    æŀĦçŃij
    -0.08
    å¼ĢéŨ
    -0.08
    æĭįæĭį
    -0.08
    é¹³
    -0.08
    POSITIVE LOGITS
    orary
    0.09
    形象
    0.09
    ÑıÑĤÑĮ
    0.09
    /be
    0.09
    .au
    0.09
    elman
    0.09
    人æ°Ķ
    0.08
    ç¶
    0.08
    éĵ
    0.08
    æķ£åıij
    0.08
    Activations Density 0.005%

    No Known Activations