© 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. 48562
    Prev
    Next
    INDEX
    Explanations

    concentration camp survivor

    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
    åı¯æĥ³èĢĮçŁ¥
    -0.10
    æĬĹéľĩ
    -0.10
    UGE
    -0.09
    æ³®
    -0.09
    uge
    -0.09
    åľ¨å®¶éĩĮ
    -0.09
    主åħ¬
    -0.09
    觥
    -0.09
    ä¸įåıĹ
    -0.08
    äºļè¿IJ
    -0.08
    POSITIVE LOGITS
    éļĶå£ģ
    0.09
     intim
    0.09
    ãĥĻãĥ«
    0.08
    brew
    0.08
    -fetch
    0.08
    exter
    0.08
    anz
    0.08
    享
    0.08
    羡
    0.08
    çİĭåĽ½
    0.08
    Activations Density 0.030%

    No Known Activations