© 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. 53388
    Prev
    Next
    INDEX
    Explanations

    DNA sequences and related processes

    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
    ¡
    -0.10
    unds
    -0.10
    quo
    -0.10
    à¹ģ
    -0.09
    ADOR
    -0.09
    eds
    -0.09
    ewise
    -0.09
    chn
    -0.09
    quette
    -0.09
    款项
    -0.09
    POSITIVE LOGITS
    çľ·
    0.10
    å©¿
    0.10
    tod
    0.10
    å±ij
    0.09
    /IP
    0.09
    emia
    0.09
    æ§İ
    0.09
    漪
    0.09
     Spears
    0.09
    åĪ¶åĵģ
    0.09
    Activations Density 0.114%

    No Known Activations