© 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. 37935
    Prev
    Next
    INDEX
    Explanations

    political party

    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
    بÙĤ
    -0.10
    åł
    -0.09
    é¦į
    -0.09
     eh
    -0.09
    çİĭèĢħ
    -0.08
    å½ĵå±Ģ
    -0.08
    éĴĿ
    -0.08
    ounter
    -0.08
    æ¯Ķäºļ
    -0.08
    éļ¾åħ³
    -0.08
    POSITIVE LOGITS
     consequential
    0.10
    åģİ
    0.09
    PED
    0.09
    metrics
    0.09
    æĭľ
    0.09
    füg
    0.09
    ance
    0.08
    åīįä¸ĸ
    0.08
    åIJĪ
    0.08
    Exposed
    0.08
    Activations Density 0.016%

    No Known Activations