© 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. 8959
    Prev
    Next
    INDEX
    Explanations

    training programs and lessons

    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
    诰
    -0.11
    æ®ĩ
    -0.09
    oggled
    -0.09
    累累
    -0.09
    avic
    -0.09
    erved
    -0.09
    ä¾ł
    -0.09
    ewood
    -0.09
    åIJĦé¡¹å·¥ä½ľ
    -0.09
     phóng
    -0.09
    POSITIVE LOGITS
    åŁ¹è®Ń
    0.11
    æĻ®åıĬ
    0.10
     programs
    0.10
     sessions
    0.10
     programmes
    0.09
    mes
    0.09
    zos
    0.09
    åŁ¹è®ŃæľºæŀĦ
    0.08
     osc
    0.08
    .Provider
    0.08
    Activations Density 0.079%

    No Known Activations