© 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. 36814
    Prev
    Next
    INDEX
    Explanations

    years or credits

    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
    dere
    -0.09
    éľģ
    -0.09
    .chapter
    -0.09
    å¿ĺ
    -0.08
    ahi
    -0.08
    chapter
    -0.08
    IMO
    -0.08
    çİĻ
    -0.08
    åĩĢ
    -0.08
    ÊĻ
    -0.08
    POSITIVE LOGITS
    å¼Ģ设
    0.09
    è¿ĩåħ³
    0.09
    èµ·æŃ¥
    0.09
    jun
    0.08
    纳åħ¥
    0.08
     COUR
    0.08
    åĵij
    0.08
    çļ²
    0.08
    é©Ń
    0.08
     juni
    0.08
    Activations Density 0.057%

    No Known Activations