© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    calling, calls, and telephone

    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
    èł¢
    -0.10
    éļIJéļIJ
    -0.10
    NBC
    -0.09
    ç»´æĿĥ
    -0.09
    ×Ļ×ł×ª
    -0.09
    å¿«æĬ¥
    -0.09
    åĩĿ
    -0.09
    æ¯Ĵ
    -0.09
    füg
    -0.09
    éħĿéħ¿
    -0.09
    POSITIVE LOGITS
    çĶµè¯Ŀ
    0.12
    æīĵçĶµè¯Ŀ
    0.11
    æĭľè®¿
    0.11
    éĽ»è©±
    0.11
     telephone
    0.09
    éĶ²
    0.09
    å¤ĸåĩº
    0.09
    æīĵæĸŃ
    0.09
    åħ¥æĪ·
    0.09
    telephone
    0.09
    Activations Density 0.046%

    No Known Activations