© 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. 51811
    Prev
    Next
    INDEX
    Explanations

    bonds and investments

    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
    åĩłåı¥
    -0.10
    绫
    -0.09
    åĿļ强
    -0.09
    æīĢéľĢè¦ģ
    -0.09
    æĿ¥è¿ĻéĩĮ
    -0.09
    è¥Ł
    -0.09
    çģŃ
    -0.09
     Animator
    -0.09
    ä¹ĭä½ľ
    -0.08
    nom
    -0.08
    POSITIVE LOGITS
    æ»ĵ
    0.10
    stry
    0.09
    à°¬
    0.09
    IFIC
    0.08
    æľ½
    0.08
     Wyatt
    0.08
    UiThread
    0.08
    çļĻ
    0.08
    ergy
    0.08
    çĶŁåij½åĬĽ
    0.08
    Activations Density 0.014%

    No Known Activations