© 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. 57299
    Prev
    Next
    INDEX
    Explanations

    Republican or Democratic Party references

    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
    æĬ¬å¤´
    -0.09
    åīįæīĢæľªæľī
    -0.09
    ogens
    -0.09
    ously
    -0.08
    çĥ¯
    -0.08
    åŃĹæ¯į
    -0.08
    arie
    -0.08
    ÙĪÙĩا
    -0.08
     ÑģоглаÑģ
    -0.08
    inn
    -0.07
    POSITIVE LOGITS
    éħ¹
    0.10
    ÑĢаÐ
    0.10
    åĽ½è¶³
    0.10
    åĭ¤åĬ³
    0.10
    çİ°æľīçļĦ
    0.09
    å¤ĦåĪĨ
    0.09
    reten
    0.09
    æĺİçŁ¥
    0.09
    OLA
    0.09
    èµĻ
    0.09
    Activations Density 0.117%

    No Known Activations