© 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. 5745
    Prev
    Next
    INDEX
    Explanations

    leftists and political leanings

    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
     conservative
    -0.14
    ä¿Ŀå®Ī
    -0.13
     conservatism
    -0.11
     conservatives
    -0.10
     Conservative
    -0.10
    arn
    -0.09
    ç¦Ģ
    -0.09
     heterosexual
    -0.09
     reactionary
    -0.09
    Trump
    -0.09
    POSITIVE LOGITS
    è¥ģ
    0.09
    éĺ´
    0.09
    éĢĨ
    0.09
    çݯä¿Ŀ
    0.09
    éĺµèIJ¥
    0.09
    触æij¸
    0.08
    çĺ«
    0.08
    渲æŁĵ
    0.08
    åĢ¾åIJij
    0.08
    éļ°
    0.08
    Activations Density 0.272%

    No Known Activations