© 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. 23831
    Prev
    Next
    INDEX
    Explanations

    people deserve to live

    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
    è´´è¿ij
    -0.09
    anted
    -0.08
     Alonso
    -0.08
    åĩºçİ°äºĨ
    -0.08
    ude
    -0.08
    æľĢæĸ°
    -0.08
    è¿İåIJĪ
    -0.08
    ä¸Ģä¸ĭåŃIJå°±
    -0.08
     incons
    -0.08
    riv
    -0.08
    POSITIVE LOGITS
    享æľī
    0.12
    éĥ½èĥ½å¤Ł
    0.10
    éĥ½èĥ½
    0.10
    享åıĹåĪ°
    0.10
    æ¤Ĵ
    0.09
    _opts
    0.09
    å¹³çŃī
    0.09
    åIJĥ饱
    0.09
    æľīæĽ´å¥½çļĦ
    0.09
     backing
    0.09
    Activations Density 0.026%

    No Known Activations