© 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. 7702
    Prev
    Next
    INDEX
    Explanations

    own career or partner

    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
    oze
    -0.10
    人æµģ
    -0.09
    åIJĪ约
    -0.09
    shm
    -0.09
    æİ°
    -0.09
    éĽı
    -0.09
    人家
    -0.09
    æľªæĪIJ
    -0.08
    çĨĬçĮ«
    -0.08
    ä½ıåľ¨
    -0.08
    POSITIVE LOGITS
    <const
    0.09
    .realm
    0.09
    æľºåħ³
    0.09
    å®īå®ģ
    0.09
    åĶ¤
    0.09
     Sever
    0.09
    ugin
    0.08
     cá»ķ
    0.08
    æ©ŁéĹľ
    0.08
    forge
    0.08
    Activations Density 0.084%

    No Known Activations