© 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. 6870
    Prev
    Next
    INDEX
    Explanations

    glory and glorious

    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
    æ·±æĥħ
    -0.09
    ermen
    -0.09
    ÑĮÑı
    -0.09
    çĿ¦
    -0.09
    é²Ľ
    -0.09
    jak
    -0.08
    饺
    -0.08
    orem
    -0.08
    ers
    -0.08
    aje
    -0.08
    POSITIVE LOGITS
    fully
    0.14
    ful
    0.12
    æĹłæ¯Ķ
    0.10
    FUL
    0.10
     glory
    0.10
     Glory
    0.09
    oyal
    0.09
    ties
    0.09
    aires
    0.08
    OLA
    0.08
    Activations Density 0.008%

    No Known Activations