© 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. 26781
    Prev
    Next
    INDEX
    Explanations

    mass

    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
     rein
    -0.09
    åħĪè¿Ľ
    -0.09
    çĪ¶åŃIJ
    -0.08
    ä¸Ģ对
    -0.08
    er
    -0.08
    æ¹Ķ
    -0.08
    æł
    -0.08
    ç¼Ĩ
    -0.08
    两项
    -0.08
    ìĸ´
    -0.08
    POSITIVE LOGITS
     маÑģÑģ
    0.11
    .mass
    0.10
     mass
    0.10
    çłĿ
    0.09
    éĩįéĩı
    0.09
    æĥ¯
    0.09
    ORN
    0.09
    ASTE
    0.09
    å©Ĩ
    0.09
     Mass
    0.09
    Activations Density 0.078%

    No Known Activations