© 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. 53390
    Prev
    Next
    INDEX
    Explanations

    keyboard input and events

    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
    æķ·
    -0.10
    绾
    -0.10
    ä¸įå¼Ģ
    -0.10
    æĺİçıł
    -0.10
    æĴij
    -0.10
    æĪijæīį
    -0.10
    åħīçħ§
    -0.09
    以èī²
    -0.09
    å¼Ģè¾Ł
    -0.09
    .Formatter
    -0.09
    POSITIVE LOGITS
    .keyboard
    0.10
     Arb
    0.09
     keyboards
    0.09
    åıĶ
    0.08
     keyboard
    0.08
    éĶ®çĽĺ
    0.08
    è¾ĵ
    0.08
     productivity
    0.08
    å·¦æīĭ
    0.08
    éĢı
    0.08
    Activations Density 0.175%

    No Known Activations