© 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. 10727
    Prev
    Next
    INDEX
    Explanations

    relative clauses

    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
    çĤ¹åĩ»æŁ¥çľĭ
    -0.11
    åł¤
    -0.08
     Lehr
    -0.08
    èįĥ
    -0.08
    rist
    -0.08
    åĺ´
    -0.08
     Daniels
    -0.08
     Malays
    -0.08
    èĵī
    -0.08
    sst
    -0.08
    POSITIVE LOGITS
    Ĥæķ°
    0.12
     OTHERWISE
    0.10
     otherwise
    0.10
    éĩĩ访æŶ
    0.10
    æĢ¥åī§
    0.09
    ä¸Ģ缴å¤Ħäºİ
    0.09
    ä¸Ģ群人
    0.09
    åºĶ该å¦Ĥä½ķ
    0.09
    æĺ¯å¤ļä¹Ī
    0.09
    åIJ¦åĪĻ
    0.09
    Activations Density 0.149%

    No Known Activations