© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59450
    Prev
    Next
    INDEX
    Explanations

    ingham or brigham 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
    Negative Logits
    ally
    -0.10
    uos
    -0.10
    çħ
    -0.10
    agal
    -0.10
    åīįæīĢ
    -0.09
    ä»Ģä¹Īäºĭæĥħ
    -0.09
    ght
    -0.09
    使çĶ¨æĿĥ
    -0.09
    ãģĥ
    -0.09
    ToOne
    -0.08
    POSITIVE LOGITS
    erk
    0.11
    lish
    0.10
    riel
    0.10
    ilton
    0.10
    èŁĨ
    0.09
    artz
    0.09
    enuity
    0.09
    æĬķèŀįèµĦ
    0.09
    former
    0.09
    å¿ĥæĦ¿
    0.09
    Activations Density 0.015%

    No Known Activations