© 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. 20799
    Prev
    Next
    INDEX
    Explanations

    minecraft

    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
    æ³ķ令
    -0.10
    鸽
    -0.10
    icals
    -0.10
    IRM
    -0.10
    ulary
    -0.09
    gies
    -0.09
    å¨ĩ
    -0.09
    encial
    -0.09
    妩
    -0.09
    CRM
    -0.09
    POSITIVE LOGITS
    çĶĵ
    0.10
    stad
    0.09
    éļį
    0.09
    çķĢ
    0.08
    ien
    0.08
    该åİ¿
    0.08
    å±ij
    0.08
    éĺĥ
    0.08
    æľīæľº
    0.08
    agen
    0.08
    Activations Density 0.057%

    No Known Activations