© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50361
    Prev
    Next
    INDEX
    Explanations

    campaigns and initiatives

    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
    åĪĽæĸ°èĥ½åĬĽ
    -0.10
    éĶ¦
    -0.09
    æł¼
    -0.08
    æī¿
    -0.08
    _mar
    -0.08
    èĢĥèĻijåĪ°
    -0.08
     TELE
    -0.08
    ä»ħ为
    -0.08
    _NR
    -0.08
     Vanity
    -0.08
    POSITIVE LOGITS
     Alive
    0.09
    æĿijåŃIJ
    0.09
    游æĪıéĩĮçļĦ
    0.09
    Together
    0.09
    èıĩ
    0.09
    Ñĩки
    0.08
    çķ¿
    0.08
    ä¸ĵ项è¡ĮåĬ¨
    0.08
    æĶ»åĬ¿
    0.08
    åĬłæ²¹
    0.08
    Activations Density 0.191%

    No Known Activations