© 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. 48395
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs or states of being

    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
    è¿Ļæĺ¯ä¸Ģç§į
    -0.11
    è¿ĻäºĽ
    -0.10
     these
    -0.09
    è¿Ļæĺ¯ä¸Ģ个
    -0.09
    以åıĬåħ¶ä»ĸ
    -0.09
    æĬĬè¿ĻäºĽ
    -0.08
    è¿ĻäºĽéĹ®é¢ĺ
    -0.08
    éĢĻäºĽ
    -0.08
    è¿ĻäºĽéĥ½æĺ¯
    -0.08
    以åıĬ
    -0.08
    POSITIVE LOGITS
    æĥłæ°ij
    0.10
    åīįéĢĶ
    0.09
    ãģĹãģĭãĤĤ
    0.09
    çľĭä¸įåĩº
    0.09
    LOTS
    0.09
     Prov
    0.09
    åŃº
    0.08
    .CreateInstance
    0.08
     nonetheless
    0.08
    utton
    0.08
    Activations Density 0.380%

    No Known Activations