© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37322
    Prev
    Next
    INDEX
    Explanations

    fight or flight, avoidance, comfort zone, attachment

    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
    GEST
    -0.10
    åĬĽåº¦
    -0.10
     Shepard
    -0.09
     cyc
    -0.09
    串
    -0.09
    æ»´
    -0.09
    ä¸Ģ代
    -0.09
    æĭIJ
    -0.09
    碼
    -0.09
    .TestCase
    -0.09
    POSITIVE LOGITS
    æģIJæĥ§
    0.09
    å¥ĭè¿Ľ
    0.09
     confront
    0.09
     вÑģего
    0.09
    umu
    0.08
    åķ¸
    0.08
    çķı
    0.08
    çŃĶåį·
    0.08
     Nobel
    0.08
     arm
    0.08
    Activations Density 0.076%

    No Known Activations