© 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. 20329
    Prev
    Next
    INDEX
    Explanations

    atheism, secularism, accommodation

    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
     sit
    -0.09
    èµŀ
    -0.09
    ales
    -0.09
    ä¸Ģå±Ĥ
    -0.09
    _hyper
    -0.09
    è¹²
    -0.08
     Lowe
    -0.08
    çħŀ
    -0.08
    åĿIJ
    -0.08
     privilege
    -0.08
    POSITIVE LOGITS
    宪æ³ķ
    0.12
    å®ĹæķĻ
    0.11
    伪
    0.11
    ç¥ľ
    0.10
    inch
    0.10
    åıµ
    0.10
    ç½Ĥ
    0.10
    æĵ¦æĭŃ
    0.09
    礼æĭľ
    0.09
    åĪĨ离
    0.09
    Activations Density 0.128%

    No Known Activations