© 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. 4860
    Prev
    Next
    INDEX
    Explanations

    registered trademarks

    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
    .unlink
    -0.09
    Bindable
    -0.08
    æĶ¹
    -0.08
     못
    -0.08
     Accord
    -0.08
    åħ¸
    -0.08
    puty
    -0.08
    åIJĪ约
    -0.08
     Kick
    -0.08
     Mounted
    -0.08
    POSITIVE LOGITS
    èĩªè§ī
    0.11
     trademarks
    0.10
    çļĦåIJįåŃĹ
    0.10
     names
    0.09
    åIJįåŃĹ
    0.09
     registered
    0.09
    åķĨæłĩ
    0.09
     trade
    0.09
     reserved
    0.09
    èij¶
    0.09
    Activations Density 0.021%

    No Known Activations