© 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. 8118
    Prev
    Next
    INDEX
    Explanations

    circuit boards

    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
     бÑĥк
    -0.09
    æ²ĥ
    -0.09
    tas
    -0.09
    olean
    -0.09
    çķİ
    -0.08
    åģľçĶµ
    -0.08
    建çŃij设计
    -0.08
    <HTMLInputElement
    -0.08
    ordo
    -0.08
    æĢĤ
    -0.08
    POSITIVE LOGITS
     Carlton
    0.11
    ihn
    0.11
    igy
    0.10
    失æķĪ
    0.10
    æĬ½
    0.09
    ÑĢай
    0.09
    uder
    0.09
    annels
    0.09
    æ²±
    0.09
    ä¸Ńä¿¡
    0.09
    Activations Density 0.382%

    No Known Activations