© 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. 37893
    Prev
    Next
    INDEX
    Explanations

    political nomination

    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
    ç½Ħ
    -0.12
    oce
    -0.10
    lyn
    -0.10
    _rw
    -0.09
    趴
    -0.09
    roys
    -0.09
    PIO
    -0.09
    ãĥIJãĥ¬
    -0.09
    磬
    -0.08
    dos
    -0.08
    POSITIVE LOGITS
    宾é¦Ĩ
    0.09
    ean
    0.09
    é«ĺä½į
    0.09
    æŀ¶åŃIJ
    0.09
    åĽ½åĬ¡éĻ¢
    0.08
    Ø·Ùħ
    0.08
    åľĪ
    0.08
    é«ĺå±Ĥ
    0.08
    åħ´èĩ´
    0.08
    æī§æĦı
    0.08
    Activations Density 0.064%

    No Known Activations