© 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. 56418
    Prev
    Next
    INDEX
    Explanations

    legal citations or case names

    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¸įå®ļ
    -0.09
    starter
    -0.09
    yat
    -0.09
    ä»ĵåĤ¨
    -0.09
    æIJģ
    -0.09
     Äijạo
    -0.09
    交æ±ĩ
    -0.09
    éĴĪ对æĢ§
    -0.09
    æľīéĴĪ对æĢ§
    -0.09
    åĴĢ
    -0.09
    POSITIVE LOGITS
    å°±è¶Ĭ
    0.10
    åłij
    0.09
    éĺ´éĺ³
    0.09
    è¾ĥ
    0.09
    omat
    0.08
    iram
    0.08
    oon
    0.08
     ÑģÑĦеÑĢе
    0.08
     kv
    0.08
    formed
    0.08
    Activations Density 0.197%

    No Known Activations