© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 27796
    Prev
    Next
    INDEX
    Explanations

    news and current 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
    åįģäºĮäºĶ
    -0.18
    éĩijèŀįå᱿ľº
    -0.16
    ç»ĻåĬĽ
    -0.15
    奥巴马
    -0.15
    æ±¶å·Ŀ
    -0.14
    æĸ°åĨľæĿij
    -0.13
     iPod
    -0.13
    åĽ½åľŁèµĦæºIJ
    -0.12
    åįļ客
    -0.12
    åıĪ好åıĪå¿«
    -0.11
    POSITIVE LOGITS
    èµĭèĥ½
    0.23
    åįģåĽĽäºĶ
    0.20
    æĬĸéŁ³
    0.18
    è¸Ķ
    0.18
    ç½ij红
    0.18
    æĸ°åŁºå»º
    0.17
    乡æĿijæĮ¯åħ´
    0.17
    çŁŃè§Ĩé¢ij
    0.16
    COVID
    0.16
    èİ·å¾ĹæĦŁ
    0.16
    Activations Density 2.752%

    No Known Activations