© 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. 20015
    Prev
    Next
    INDEX
    Explanations

    Cornell Medical, Cornelius

    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
    åѦåīį
    -0.09
    欲
    -0.09
    æĸIJ
    -0.09
    edd
    -0.08
    أ
    -0.08
     пÑĢоÑģмоÑĤÑĢ
    -0.08
    ÑIJ
    -0.08
    rescia
    -0.08
    èį·
    -0.08
    etter
    -0.08
    POSITIVE LOGITS
    ists
    0.12
    çī¹æ´¾
    0.09
    itate
    0.09
    ÑģÑĭ
    0.09
    igung
    0.09
    izabeth
    0.09
    AMY
    0.09
    æİ¥çĿĢ
    0.09
    หม
    0.09
    ers
    0.09
    Activations Density 0.003%

    No Known Activations