© 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. 35770
    Prev
    Next
    INDEX
    Explanations

    sequence of events

    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
    ä¸įåĪ°
    -0.11
    åīįä¸Ģ天
    -0.09
    æŁ¥çľĭ详æĥħ
    -0.09
    æĹłçĸij
    -0.09
    ä¸įä¹ħ
    -0.09
    èģĨ
    -0.09
    ä¸Ģåı·
    -0.08
    RIES
    -0.08
    éĻ¶
    -0.08
    èŀį
    -0.08
    POSITIVE LOGITS
    åĨ³
    0.09
    çĦ¶åIJİ
    0.08
     buz
    0.08
     then
    0.08
    ankan
    0.08
    说ä»Ģä¹Ī
    0.08
    æıł
    0.08
    åĪĩãĤĬ
    0.08
    cores
    0.08
    Ñĺ
    0.08
    Activations Density 0.053%

    No Known Activations