© 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. 36189
    Prev
    Next
    INDEX
    Explanations

    pressure, nerves, anxiety

    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
    æģķ
    -0.12
    æĭĵ
    -0.10
    å¹²éĥ¨éĺŁä¼į
    -0.10
    æĩĴå¾Ĺ
    -0.10
    åŃĿ
    -0.10
    毫ä¸įçĬ¹è±«
    -0.09
    å¸ij
    -0.09
    éľģ
    -0.09
    çĿ£
    -0.09
    åĬ©éķ¿
    -0.09
    POSITIVE LOGITS
    ç´§å¼ł
    0.15
     nerves
    0.13
     nervous
    0.13
    å¤ĩæĪĺ
    0.12
    åıijæĮ¥
    0.12
    çĦ¦èĻij
    0.12
     nerv
    0.12
    å¿IJ
    0.12
     anxiety
    0.11
    èĢĥåľº
    0.11
    Activations Density 0.048%

    No Known Activations