© 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. 49292
    Prev
    Next
    INDEX
    Explanations

    previous / previously

    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
    erva
    -0.09
    gres
    -0.09
    çĦī
    -0.09
    ç¥Ģ
    -0.09
     Ñĥзн
    -0.09
    çľ¼çķĮ
    -0.08
    é¢
    -0.08
    亲çĪ±
    -0.08
    asury
    -0.08
    -middle
    -0.08
    POSITIVE LOGITS
     previous
    0.26
     previously
    0.24
    以å¾Ģ
    0.23
    æѤåīį
    0.23
    以åīį
    0.21
    æĽ¾åľ¨
    0.21
    æĽ¾
    0.21
    æĽ¾ç»ı
    0.21
    previous
    0.20
    ä¹ĭåīį
    0.20
    Activations Density 0.452%

    No Known Activations