© 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. 52036
    Prev
    Next
    INDEX
    Explanations

    sequential actions or outcomes

    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
    æĹ©åľ¨
    -0.10
    STANCE
    -0.09
    æĺĤ
    -0.09
    大åħ¨
    -0.09
    åĶ®
    -0.08
    CodeAt
    -0.08
    æŃ¤ä¸¾
    -0.08
    å¤įèĭı
    -0.08
    wers
    -0.08
    à¹Ģส
    -0.08
    POSITIVE LOGITS
    è¦ģä¹Ī
    0.12
    äºĨä¸Ģç³»åĪĹ
    0.12
    ä¸Ģç³»åĪĹ
    0.11
    缸åºĶçļĦ
    0.10
    åĪĿæŃ¥
    0.10
     далÑĮн
    0.10
    çĦ¶åIJİ
    0.10
     then
    0.10
     Either
    0.09
    建ç«ĭèµ·
    0.09
    Activations Density 0.105%

    No Known Activations