© 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. 11679
    Prev
    Next
    INDEX
    Explanations

    news, allegations, situation, sale, incident

    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
    æħ¬
    -0.09
    çİ°æľīçļĦ
    -0.09
    åİŁæľī
    -0.09
    æľ¬èº«å°±æĺ¯
    -0.08
    å¾Ģå¾Ģ
    -0.08
    .snp
    -0.08
     оказ
    -0.08
    æ¯Ķå¦Ĥ
    -0.08
    æģĭçĪ±
    -0.08
    ainer
    -0.08
    POSITIVE LOGITS
    举åĬ¨
    0.10
    该æĢİä¹ĪåĬŀ
    0.09
    æĢİä¹ĪåĽŀäºĭ
    0.09
    æŃ¤ä¸¾
    0.09
    æĢİä¹ĪåĬŀ
    0.09
    çªģå¦Ĥåħ¶æĿ¥
    0.09
    å·®çĤ¹
    0.09
    ä¸İæŶ
    0.09
    æѤäºĭ
    0.09
    è¿Ļ件äºĭæĥħ
    0.09
    Activations Density 0.099%

    No Known Activations