© 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. 48389
    Prev
    Next
    INDEX
    Explanations

    pregnancy and body changes

    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
    è´°
    -0.10
    æĥ¨
    -0.09
    /features
    -0.09
    ãģŃ
    -0.09
    说åĪ°è¿ĻéĩĮ
    -0.09
    eneg
    -0.08
    èĩªè´Ł
    -0.08
    aso
    -0.08
    主è¦ģé¢Ĩ导
    -0.08
    ìĭ
    -0.08
    POSITIVE LOGITS
    åĩĨ
    0.10
    _REASON
    0.10
    æģŃåĸľ
    0.10
    åŃķæľŁ
    0.09
    æĦŁåħ´è¶£
    0.09
    _closure
    0.09
    å»ĵ
    0.09
     Colo
    0.08
    æĩ¿
    0.08
    ä»İåīį
    0.08
    Activations Density 0.101%

    No Known Activations