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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 36313
    Prev
    Next
    INDEX
    Explanations

    government management and services

    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¯éĿŀ
    -0.12
    å΍
    -0.11
    åįĩåѦ
    -0.10
    积æŀģæİ¢ç´¢
    -0.09
    horn
    -0.09
    æīĴ
    -0.09
    广æĴŃç͵è§Ĩ
    -0.09
    -sync
    -0.09
    åıijåĬ¨
    -0.09
    atan
    -0.09
    POSITIVE LOGITS
    æĶ¿åºľéĩĩè´Ń
    0.12
    åħ¬åĬ¡åijĺ
    0.12
    缴å±ŀ
    0.10
    æĭĽ
    0.10
     bure
    0.10
    åį°ç«ł
    0.09
    éĩĩè´Ń
    0.09
    饷
    0.09
    åľ¨äº¬
    0.09
    éŀ£
    0.09
    Activations Density 0.087%

    No Known Activations