© 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. 21514
    Prev
    Next
    INDEX
    Explanations

    allegedly engaging

    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
    æĪ·
    -0.10
    çİ«
    -0.10
    æ¦Ľ
    -0.09
    ä¾®
    -0.09
    ç«ŀ
    -0.09
    åı¦ä¸Ģä½į
    -0.09
    楯
    -0.09
    rif
    -0.09
    ç±³ç²ī
    -0.09
    çĶŁèĤĸ
    -0.08
    POSITIVE LOGITS
    InitStruct
    0.11
    ä¸Ĭå¸Ĥåħ¬åı¸
    0.10
    .jupiter
    0.09
     Washer
    0.09
    æķijåij½
    0.09
    èĤ¡ä»½
    0.09
    èĤ¡æĿĥ
    0.09
    æĸ°èĤ¡
    0.09
    对åħ¬åı¸
    0.09
    éĢīèĤ¡
    0.09
    Activations Density 0.068%

    No Known Activations