© 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. 37606
    Prev
    Next
    INDEX
    Explanations

    Jay names and entities

    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
    INAL
    -0.10
    åķ¬
    -0.10
    inal
    -0.09
    ItemAt
    -0.09
    ëĿ¼ëıĦ
    -0.09
    ELS
    -0.09
    æµļ
    -0.09
    éĴ±å¸ģ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    uro
    -0.08
    POSITIVE LOGITS
    ishly
    0.10
    hawk
    0.10
    ish
    0.10
    ernet
    0.10
    çĪ·
    0.09
    ifications
    0.09
    à¹Ģà¸īà¸ŀาะ
    0.09
    ification
    0.09
    ings
    0.09
    ify
    0.09
    Activations Density 0.013%

    No Known Activations