© 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. 19661
    Prev
    Next
    INDEX
    Explanations

    keratectomy

    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
    æ½
    -0.09
    çļĦæĪIJéķ¿
    -0.09
    以èī²
    -0.09
     поÑĩ
    -0.09
    URN
    -0.09
    çī¹æ´¾åijĺ
    -0.09
    é¢Ī
    -0.09
    æĺ¾
    -0.09
     carc
    -0.09
    éij
    -0.08
    POSITIVE LOGITS
    é©¿
    0.09
     resid
    0.09
    _outline
    0.09
    çī§
    0.08
    oplast
    0.08
    åħīçݯ
    0.08
    ä¹°åĪ°
    0.08
    Opens
    0.08
    åıijå¸ĥä¼ļä¸Ĭ
    0.08
    _opts
    0.08
    Activations Density 0.182%

    No Known Activations