© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37078
    Prev
    Next
    INDEX
    Explanations

    veteran, agent, survivor, ex-con

    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
    éĽı
    -0.10
    MISS
    -0.09
    endet
    -0.09
    åĢĻ
    -0.09
    tro
    -0.09
    å¤ĩèĢĥ
    -0.09
    ä¸Ģè´¯
    -0.09
    åĤ¬çĶŁ
    -0.09
    æĺ¯æĢİæł·
    -0.08
    æį
    -0.08
    POSITIVE LOGITS
    åĪ¶åº¦æĶ¹éĿ©
    0.10
    æ®ĭçĸ¾
    0.08
     Lans
    0.08
    çĻĥ
    0.08
    æ¯ĽçĹħ
    0.08
     ResourceType
    0.08
    澡
    0.08
    Îĸ
    0.08
     Dunn
    0.08
    æģ©
    0.07
    Activations Density 0.041%

    No Known Activations