© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21365
    Prev
    Next
    INDEX
    Explanations

    raised funding amounts

    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
    æ»ŀ
    -0.10
    çķı
    -0.09
    orne
    -0.09
    _sink
    -0.09
    åĮ¾
    -0.09
    æĽ²æĬĺ
    -0.09
    ç¹ģ
    -0.08
    Bindable
    -0.08
    lag
    -0.08
    лÑĥ
    -0.08
    POSITIVE LOGITS
    çŃ¾çº¦
    0.10
    à¹īว
    0.10
    çĪ±ç¾İ
    0.10
    棣
    0.09
     backers
    0.09
    æīĢéľĢ
    0.09
    ä¹Łå¥½
    0.09
    æĦļ
    0.08
    äºĨå¤ļå°ij
    0.08
    æĸ¼æĺ¯
    0.08
    Activations Density 0.039%

    No Known Activations