© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    friend interactions

    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
    å¿ĥæĦı
    -0.11
    åŃĺåľ¨äºİ
    -0.09
    大éģĵ
    -0.09
    uft
    -0.08
    æīĩ
    -0.08
    endet
    -0.08
     Sweet
    -0.08
    é«Ń
    -0.08
    èĢģ头
    -0.08
    pbs
    -0.08
    POSITIVE LOGITS
    ä¸ĭçıŃ
    0.11
     thereof
    0.10
    innen
    0.09
    èĬĻèĵī
    0.09
    uml
    0.09
    nels
    0.09
    lessly
    0.09
    å¾Ĺèµ·
    0.09
    Ñģкого
    0.09
    CKER
    0.08
    Activations Density 0.029%

    No Known Activations