© 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. 54947
    Prev
    Next
    INDEX
    Explanations

    award nominations

    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»İåīį
    -0.10
    çļĦåIJĦç§į
    -0.10
    åIJĦç§į
    -0.10
    æĪĸå¤ļæĪĸå°ij
    -0.10
     Ole
    -0.09
    å«©
    -0.09
    Touches
    -0.09
    çļĦä¸ĢäºĽ
    -0.09
    -NLS
    -0.08
    é«ĺåħ´
    -0.08
    POSITIVE LOGITS
    åįķ项
    0.10
    çł´
    0.09
    ÑģпоÑĢ
    0.09
    å®ľå±ħ
    0.09
    æĹ¥çĶµ
    0.09
    èħIJ
    0.08
    第ä¸ĢåIJį
    0.08
    驾
    0.08
    åĬŀå®ŀäºĭ
    0.08
    äºĭå®ŀ
    0.08
    Activations Density 0.094%

    No Known Activations