© 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. 51721
    Prev
    Next
    INDEX
    Explanations

    links or sources

    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
    igham
    -0.11
    bie
    -0.11
    neck
    -0.11
    ÑģÑĮ
    -0.11
    ĺ
    -0.11
    ãģĦãģĨ
    -0.10
    ../../../
    -0.10
    ãģªãģĭãģªãģĭ
    -0.10
    ogy
    -0.09
    pository
    -0.09
    POSITIVE LOGITS
    ãģĹãģ¾ãģĨ
    0.12
    çħ
    0.10
    oire
    0.10
    naire
    0.10
    ر
    0.10
    ingly
    0.09
    æѤåĪ»
    0.09
    antas
    0.09
     shady
    0.09
    åŃIJéĩĮ
    0.09
    Activations Density 0.055%

    No Known Activations