© 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. 51696
    Prev
    Next
    INDEX
    Explanations

    special operationsmilitary unitsRaid and operationsblog commentsinvention relatessingle screen

    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
    ilm
    -0.10
    å¤©åľ°
    -0.09
    æĹłè¾ľ
    -0.09
     pseud
    -0.09
    rail
    -0.09
    æĬµæĮ¡
    -0.09
    ç¾½æ¯Ľ
    -0.09
    ä»ħ次äºİ
    -0.09
    enders
    -0.08
    çĽ¾
    -0.08
    POSITIVE LOGITS
    å·¥ç¨ĭæĬĢæľ¯
    0.09
    drs
    0.08
    è±¹
    0.08
    æĢ§è´¨
    0.08
     dri
    0.08
    ijľ
    0.08
    è¾¾å°Ķ
    0.08
    etta
    0.08
    æĬĢæľ¯çłĶåıij
    0.08
    _operations
    0.08
    Activations Density 0.109%

    No Known Activations