© 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. 35850
    Prev
    Next
    INDEX
    Explanations

    future events and sequencing

    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
    çĻ¾ä¸ĩ
    -0.10
    åħ¨æĹ¥
    -0.09
    å°ıæŶåīį
    -0.09
    è¿Ľåĩº
    -0.09
    åģľçīĮ
    -0.08
    eten
    -0.08
    éĢĨ
    -0.08
    åīįæīĢæľªæľī
    -0.08
    çĽijè§Ĩ
    -0.08
    ä¸ĭå·´
    -0.08
    POSITIVE LOGITS
     later
    0.23
    åIJİæĿ¥
    0.19
    Later
    0.19
     Later
    0.19
    later
    0.18
    åIJİæľŁ
    0.17
    å¾Įä¾Ĩ
    0.15
     später
    0.14
     później
    0.13
    以åIJİ
    0.11
    Activations Density 0.053%

    No Known Activations