© 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. 30214
    Prev
    Next
    INDEX
    Explanations

    charged and guilty pleas

    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
    å·«
    -0.10
     affairs
    -0.09
    æĪı
    -0.08
    é£İåħī
    -0.08
    äºĭåĬ¡
    -0.08
    票
    -0.08
    çij°
    -0.08
    кÑĢа
    -0.08
     Affairs
    -0.08
    atum
    -0.08
    POSITIVE LOGITS
    TP
    0.09
    å®īåħ¨éļIJæĤ£
    0.09
    ordon
    0.09
    apsed
    0.09
    å«Ĥ
    0.08
    ordan
    0.08
    ç½ijåıĭ
    0.08
    æ¹¿åľ°
    0.08
    æĻ¾
    0.08
     бо
    0.08
    Activations Density 0.136%

    No Known Activations