© 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. 37980
    Prev
    Next
    INDEX
    Explanations

    beliefs and convictions

    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
    -sama
    -0.09
     attention
    -0.09
    æĨĶ
    -0.08
    æĴĤ
    -0.08
    ä¸ĩ象
    -0.08
    ستر
    -0.08
     fame
    -0.08
    ond
    -0.07
    ä¹ı
    -0.07
    jing
    -0.07
    POSITIVE LOGITS
     beliefs
    0.18
    信念
    0.18
    åĿļä¿¡
    0.17
     belief
    0.17
    çĽ¸ä¿¡
    0.16
     convictions
    0.16
    ç¬ĥ
    0.14
     believes
    0.14
     conviction
    0.13
    ä¿¡ä»°
    0.13
    Activations Density 0.059%

    No Known Activations