© 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. 57961
    Prev
    Next
    INDEX
    Explanations

    past tense verbs followed by numbers or quantities

    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
    æŀģ大çļĦ
    -0.10
    ä»İå°ı
    -0.10
    æµĵåİļ
    -0.09
    è¶³å¤Ł
    -0.09
    åĩłæŃ¥
    -0.09
    è¶ħæłĩ
    -0.09
    çļĦ帮åĬ©ä¸ĭ
    -0.09
    ä»°
    -0.09
    说å®ŀè¯Ŀ
    -0.09
    å¬ī
    -0.08
    POSITIVE LOGITS
    綦
    0.09
    ä¸İæѤ
    0.09
     lòng
    0.08
    æŶéĹ´ä¸º
    0.08
    quiv
    0.08
    身ä¸Ĭ
    0.08
    å½³
    0.08
    ť
    0.08
     rst
    0.08
     vale
    0.08
    Activations Density 0.188%

    No Known Activations