© 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. 8368
    Prev
    Next
    INDEX
    Explanations

    time format or clock

    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°Ķæĸ¯
    -0.09
    çIJĽ
    -0.08
    ocker
    -0.08
    诸èijĽ
    -0.08
    å¸ĤæĶ¿
    -0.08
    åħ´èµ·
    -0.08
    é£ı
    -0.08
    zion
    -0.08
     coding
    -0.08
    å¤ĩæ¡Ī
    -0.08
    POSITIVE LOGITS
    ISTER
    0.09
    Interop
    0.09
    渡
    0.09
    å¾Īå¿«å°±
    0.09
    æ¿Ĵ
    0.09
    ssel
    0.08
    æĪij们å°Ĩ
    0.08
    åı¯ä»¥ä»İ
    0.08
    elig
    0.08
    éĤĭ
    0.08
    Activations Density 0.039%

    No Known Activations