© 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. 19169
    Prev
    Next
    INDEX
    Explanations

    others

    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
    ä¸Ģ个人
    -0.10
    éĢĴç»Ļ
    -0.09
    -mf
    -0.09
    ä¸İåħ¶ä»ĸ
    -0.09
    çķĻç»Ļ
    -0.09
    人们对
    -0.08
    åIJij社ä¼ļ
    -0.08
    åĪ°çİ°åľ¨
    -0.08
    缸å½ĵ
    -0.08
    å¼Ħ
    -0.08
    POSITIVE LOGITS
    nier
    0.09
     нап
    0.08
    篮
    0.08
    ä¸Ģç¬ij
    0.08
    izr
    0.08
    ware
    0.08
    åħķ
    0.08
    æīĭèħķ
    0.08
    æĬķ
    0.08
    ä¸ĢçĶŁ
    0.08
    Activations Density 0.035%

    No Known Activations