© 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. 58844
    Prev
    Next
    INDEX
    Explanations

    strength and durability

    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
    Toolkit
    -0.10
    çħ¦
    -0.09
    è¿·
    -0.09
    çļĦç¾İ好
    -0.09
    ç»Ī身
    -0.09
    çĥº
    -0.09
    æĺ¯æĢİæł·
    -0.09
    å¾Īæ¼Ĥ亮
    -0.09
    argest
    -0.08
    ayan
    -0.08
    POSITIVE LOGITS
    æĢ§å¼º
    0.10
    çºł
    0.09
     Pins
    0.09
    åĵ¥ä¼¦æ¯Ķäºļ
    0.09
     pins
    0.08
    èĢIJçĶ¨
    0.08
    tere
    0.08
    ä¹Ĥ
    0.08
    康
    0.08
     Martial
    0.08
    Activations Density 0.050%

    No Known Activations