© 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. 54495
    Prev
    Next
    INDEX
    Explanations

    composite layered chip package

    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»ģ
    -0.10
    å°±çŁ¥éģĵ
    -0.10
    çļĦå¿ĥæĥħ
    -0.09
    éĤº
    -0.09
    离
    -0.09
    å·¥åħ·
    -0.09
    æį¶
    -0.09
    åī½
    -0.09
    (tool
    -0.08
    顺åĪ©
    -0.08
    POSITIVE LOGITS
     Bett
    0.09
    积
    0.09
    åĩºåĽ½çķĻåѦ
    0.08
    شد
    0.08
    æ°Ķ象
    0.08
    çłĸ
    0.08
    å¼ĢæĶ¯
    0.08
     immun
    0.08
    åĨįåİ»
    0.07
    æĸ°æ¨¡å¼ı
    0.07
    Activations Density 0.104%

    No Known Activations