© 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. 61688
    Prev
    Next
    INDEX
    Explanations

    religious and existential conflict

    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
    åIJĵå¾Ĺ
    -0.09
    å¦ĤæĦı
    -0.09
    è¿ĩ度
    -0.09
    æŀķ头
    -0.09
     shifted
    -0.09
    ç»ļ
    -0.08
    åĥ¦
    -0.08
    GRE
    -0.08
    éĺ²åį«
    -0.08
    禾
    -0.08
    POSITIVE LOGITS
    åĽŀ头
    0.10
    è°ħ
    0.10
    axon
    0.09
     coal
    0.09
    vc
    0.08
    宥
    0.08
    ä¸Ģè§Ĵ
    0.08
    罪
    0.08
    ä½İä½į
    0.08
    æ±ł
    0.08
    Activations Density 0.022%

    No Known Activations