© 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. 34725
    Prev
    Next
    INDEX
    Explanations

    how + adjective

    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
    é¹Ħ
    -0.11
    è±¹
    -0.11
    ä¸Ģ声
    -0.10
    çIJĨæĻº
    -0.09
    å¿ĥçģµ
    -0.09
    ç¼ģ
    -0.09
    emed
    -0.09
    resse
    -0.09
    å¼Ģåĩº
    -0.09
    主è¦ģåĨħ容
    -0.09
    POSITIVE LOGITS
    å¦Ĥä½ķ
    0.12
    çļĦéĩįè¦ģæĢ§
    0.11
    åºĶ该å¦Ĥä½ķ
    0.11
    å¤ļä¹Ī
    0.10
    çļĦåIJĦç§į
    0.10
     upcoming
    0.10
    æĺ¯å¤ļä¹Ī
    0.10
    æľīå¤ļä¹Ī
    0.09
    specs
    0.09
    æŁIJ
    0.09
    Activations Density 0.075%

    No Known Activations