© 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. 35895
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    涨
    -0.10
     favour
    -0.09
    å¾Ĺ太
    -0.09
    æĪijåıĪ
    -0.09
     myself
    -0.09
    rome
    -0.08
    ROME
    -0.08
    Cr
    -0.08
    (padding
    -0.08
    åı«æĪij
    -0.08
    POSITIVE LOGITS
     somewhere
    0.10
    probably
    0.10
    ä¸Ģå®ļæĺ¯
    0.10
    æĪĸå¤ļæĪĸå°ij
    0.10
    æĥ³å¿ħ
    0.10
     probably
    0.10
    å¼Ģè¾Ł
    0.09
    ä¸ĭè¾¾
    0.09
    å±ķå¼Ģ
    0.09
    ç»ĿæľĽ
    0.09
    Activations Density 0.080%

    No Known Activations