© 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. 39169
    Prev
    Next
    INDEX
    Explanations

    up followed by common words

    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
    åij¼åĶ¤
    -0.11
    ä»Ģä¹Īéĥ½ä¸į
    -0.11
    ç£ħ
    -0.10
    éħ±æ²¹
    -0.09
    åĽ¾æĸĩ
    -0.09
    ä¸Ģçľ¼
    -0.09
    åĬ£
    -0.09
    ä»ĵ
    -0.09
    稳å®ļçļĦ
    -0.09
    çľĭäºĨä¸Ģçľ¼
    -0.09
    POSITIVE LOGITS
    æķĻè®Ń
    0.09
    åīįæĻ¯
    0.08
    妥åĸĦ
    0.08
    èĢĢ
    0.08
    åĴĸ
    0.08
    udies
    0.08
    éľĸ
    0.08
    ALAR
    0.08
    åĨ»ç»ĵ
    0.08
    æŃ¢
    0.08
    Activations Density 0.030%

    No Known Activations