© 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. 50285
    Prev
    Next
    INDEX
    Explanations

    legal disclaimers, permissions, or warranties

    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
    èģªæĺİ
    -0.10
    éļı
    -0.10
    éļıæŶ
    -0.09
    Gatt
    -0.08
    subtype
    -0.08
    ilet
    -0.08
    Hell
    -0.08
    ye
    -0.08
    åĬł
    -0.08
    judge
    -0.07
    POSITIVE LOGITS
    ä¸ĢåĪ»
    0.10
    éºĩ
    0.10
    è¿ĻäºĽäºº
    0.10
    prof
    0.09
    çļĦçĶ»éĿ¢
    0.09
    çķĮçļĦ
    0.09
    åħļçļĦé¢Ĩ导
    0.09
    ä¸ĢéĿ¢
    0.09
    éļ¶å±ŀäºİ
    0.09
    çķĮ
    0.09
    Activations Density 0.041%

    No Known Activations