© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32604
    Prev
    Next
    INDEX
    Explanations

    historical and ecological timing

    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
     anonym
    -0.08
    涸
    -0.08
    åĮ¿åIJį
    -0.08
    æ²¥
    -0.08
    æĦıè¯Ĩ
    -0.08
    IT
    -0.08
    æ¤įæłij
    -0.08
     Woods
    -0.08
    æłijæŀĿ
    -0.08
    丼æŀĹ
    -0.08
    POSITIVE LOGITS
     Timing
    0.10
    timing
    0.10
     timing
    0.09
    _timing
    0.09
    _MEDIUM
    0.09
    ç´«èī²
    0.09
    å¥
    0.09
    -large
    0.09
    åĵ®
    0.09
    wä
    0.09
    Activations Density 0.106%

    No Known Activations