© 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. 36322
    Prev
    Next
    INDEX
    Explanations

    life and death outcomes

    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
    ç»ĪçĶŁ
    -0.10
    ç»Ī身
    -0.10
    igators
    -0.10
    ä¸įåIJĮç¨ĭ度
    -0.09
    ourt
    -0.09
    åħ»èĢģ
    -0.09
    ENTE
    -0.09
    å°¾
    -0.09
     bada
    -0.09
    /conf
    -0.09
    POSITIVE LOGITS
     Pearce
    0.09
    Pear
    0.09
    æ´¾åĩº
    0.09
    åħīçݯ
    0.08
    çªĪ
    0.08
    å°ıå§IJ
    0.08
    born
    0.08
    ä¿¡æģ¯ç³»ç»Ł
    0.08
    éŸ
    0.08
     hyp
    0.07
    Activations Density 0.118%

    No Known Activations