© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47532
    Prev
    Next
    INDEX
    Explanations

    known as

    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
    Negative Logits
    chos
    -0.10
    ำ
    -0.08
     vie
    -0.08
    ä¸ĢåıĮ
    -0.08
    侬
    -0.08
    æ¤į
    -0.08
    åīį身
    -0.08
    åĩºå¤Ħ
    -0.07
    -With
    -0.07
    åīįä»»
    -0.07
    POSITIVE LOGITS
    åı«åģļ
    0.21
    åIJįåı«
    0.21
    åIJį为
    0.19
     called
    0.16
    åı«
    0.16
    称为
    0.14
    called
    0.14
    称ä¹ĭ为
    0.13
     Called
    0.11
    红æĺŁ
    0.11
    Activations Density 0.229%

    No Known Activations