© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2524
    Prev
    Next
    INDEX
    Explanations

    received attention

    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
    mits
    -0.10
    etag
    -0.10
    æĺĮ
    -0.09
    ess
    -0.09
    çļĦä¼ĺåĬ¿
    -0.09
    éĻįä½İæĪIJæľ¬
    -0.08
    æĶ¥
    -0.08
     Batt
    -0.08
    é¹ħ
    -0.08
    .cv
    -0.08
    POSITIVE LOGITS
     attention
    0.19
     внимание
    0.16
    attention
    0.16
    åħ³æ³¨
    0.16
    Attention
    0.16
     Attention
    0.15
    éĩįçĤ¹åħ³æ³¨
    0.15
    çļĦåħ³æ³¨
    0.14
    éĹľæ³¨
    0.13
     вним
    0.13
    Activations Density 0.081%

    No Known Activations