© 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. 56287
    Prev
    Next
    INDEX
    Explanations

    physical discomfort and pressure

    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
    æ¼Ĥ
    -0.10
    åį§
    -0.09
    é«ĺ涨
    -0.09
    å¹³æŶ
    -0.09
    çģ¿
    -0.09
    ä¸ľæµ·
    -0.09
    绵
    -0.09
    grim
    -0.09
    çĩ®
    -0.09
    //{{
    -0.08
    POSITIVE LOGITS
    WAYS
    0.10
    å®ŀæķĪ
    0.09
    hg
    0.09
    åĪĨå¼Ģ
    0.09
    guard
    0.08
     compression
    0.08
    Compression
    0.08
    æĿµ
    0.08
    é¾Ł
    0.08
     Bills
    0.08
    Activations Density 0.090%

    No Known Activations