© 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. 55174
    Prev
    Next
    INDEX
    Explanations

    at home

    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
    ç«¥
    -0.08
    erd
    -0.08
    æѧ
    -0.08
    anke
    -0.08
    éĶħ
    -0.08
     ngá»Ļ
    -0.08
    éŨåīį
    -0.08
    åĪ¶åīĤ
    -0.08
    è¯ģçĽij
    -0.08
    ç»Ŀä¸į
    -0.08
    POSITIVE LOGITS
    åľ¨å®¶éĩĮ
    0.18
    åľ¨å®¶
    0.15
     home
    0.15
    åĽŀåĪ°å®¶
    0.14
    家éĩĮ
    0.14
    家ä¸Ń
    0.13
     дома
    0.13
    åĽŀ家
    0.13
    -home
    0.12
    home
    0.11
    Activations Density 0.038%

    No Known Activations