© 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. 48005
    Prev
    Next
    INDEX
    Explanations

    what's up with / how come / what's the deal

    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
    äºĽä»Ģä¹Ī
    -0.12
    èįī
    -0.10
     gì
    -0.10
    åģļä»Ģä¹Ī
    -0.09
    ä»Ģä¹Īæł·
    -0.09
    ä»Ģä¹Īåľ°æĸ¹
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    æĺ¯ä¸Ģ件
    -0.09
    æľīä»Ģä¹Ī
    -0.09
    è¿Ļ件äºĭæĥħ
    -0.09
    POSITIVE LOGITS
    èįĥ
    0.09
    tes
    0.09
     Musk
    0.09
    ute
    0.08
    une
    0.08
    eme
    0.08
    uzu
    0.08
     Rut
    0.08
    еÑĢж
    0.08
    ÑĥÑĤ
    0.08
    Activations Density 0.012%

    No Known Activations