© 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. 7627
    Prev
    Next
    INDEX
    Explanations

    Raider fans, Crypt of Tears

    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
    忱
    -0.09
    ersist
    -0.09
    é»İæĺİ
    -0.09
    ä¿Ĭ
    -0.09
    oden
    -0.08
    马路
    -0.08
    æĸĹå¿Ĺ
    -0.08
    çģ¶
    -0.08
    elts
    -0.08
    容éĩı
    -0.08
    POSITIVE LOGITS
    è£ħå¤ĩ
    0.10
    å®ĿèĹı
    0.09
    éģĹ迹
    0.09
     Barnes
    0.09
    æĸ¯åĿ¦
    0.09
    解å¼Ģ
    0.09
    æ²³æµģåŁŁ
    0.08
    /bower
    0.08
    éģĹ产
    0.08
    avia
    0.08
    Activations Density 0.035%

    No Known Activations