© 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. 21904
    Prev
    Next
    INDEX
    Explanations

    only, sole, unique

    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
     VÅ©
    -0.09
    aton
    -0.09
    éĺŁä¼į
    -0.09
     ÑĢей
    -0.09
    èĭĮ
    -0.09
    åħĪçĶŁ
    -0.09
    .getView
    -0.09
    даÑĩи
    -0.09
     Hop
    -0.09
    ides
    -0.09
    POSITIVE LOGITS
    åĶ¯ä¸Ģ
    0.27
    æĥŁ
    0.24
    åĶ¯ä¸ĢçļĦ
    0.23
     единÑģÑĤв
    0.21
    åĶ¯æľī
    0.18
    ä»ħæľī
    0.17
    åĶ¯
    0.17
     sole
    0.17
    çĭ¬ä¸Ģ
    0.17
     اÙĦÙĪØŃÙĬد
    0.17
    Activations Density 0.093%

    No Known Activations