© 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. 36053
    Prev
    Next
    INDEX
    Explanations

    information transmitted

    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
    çĵ¦
    -0.10
    eken
    -0.10
     CHUNK
    -0.09
    åıĺæĢģ
    -0.09
    缩
    -0.09
    æijĩ
    -0.09
    å¤ĸæĿ¥
    -0.09
    常è¯Ĩ
    -0.09
    讨åİĮ
    -0.09
    æĤ¬æµ®
    -0.09
    POSITIVE LOGITS
    ä¹ĭå¤ľ
    0.10
    è½®
    0.09
    人æķ°
    0.09
    еÑģÑĤи
    0.08
    zung
    0.08
    çħ¤
    0.08
     Georg
    0.08
    æ³Ħ
    0.08
    åĩĨå¤ĩ好
    0.08
    念
    0.08
    Activations Density 0.041%

    No Known Activations