© 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. 23595
    Prev
    Next
    INDEX
    Explanations

    downloaded, created, or previously existing items

    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
    åįĹæĸ¹
    -0.11
    çĶ¥
    -0.10
    举åįĹ
    -0.09
    ä¸Ģ座
    -0.09
    iani
    -0.09
    æŃ»åIJİ
    -0.09
    è¿ĩåIJİ
    -0.09
    Southern
    -0.09
    è¥Ħ
    -0.09
    brook
    -0.09
    POSITIVE LOGITS
    åĪļæīį
    0.17
     ÑĢанее
    0.15
     earlier
    0.14
     previously
    0.10
     Earlier
    0.10
    åĪļåĪļ
    0.10
    æѤåĪ»
    0.10
    æĸ¹æīį
    0.10
    åīįè¿°
    0.10
    Earlier
    0.09
    Activations Density 0.048%

    No Known Activations