© 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. 8580
    Prev
    Next
    INDEX
    Explanations

    longitudinal study

    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
    å¢ĥçķĮ
    -0.09
    ÑĤÑĢ
    -0.09
    çŃĽéĢī
    -0.08
    åĶĩ
    -0.08
    èĥľä»»
    -0.08
    宫
    -0.08
     remix
    -0.08
    eries
    -0.08
    ategy
    -0.08
    æĶ¶å½ķ
    -0.08
    POSITIVE LOGITS
    éĢĸ
    0.10
    amas
    0.09
    hua
    0.09
    çłĶ究表æĺİ
    0.09
    æĻĶ
    0.09
     жид
    0.08
    ÑĢеÑģ
    0.08
    ARCH
    0.08
    åķĨæĬ¥
    0.08
    ãĤ·ãĥ³
    0.08
    Activations Density 0.129%

    No Known Activations