© 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. 6382
    Prev
    Next
    INDEX
    Explanations

    opposite sides or ends

    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
    åħ¨å®¶
    -0.11
    æķ´ä¸ªäºº
    -0.10
    ç»
    -0.09
    rats
    -0.09
    è£
    -0.09
    伪è£ħ
    -0.09
    åħį
    -0.09
    LEASE
    -0.09
    zens
    -0.08
     Suite
    -0.08
    POSITIVE LOGITS
    åIJĦæľī
    0.13
    åIJĦèĩª
    0.12
    åĪĨåĪ«
    0.11
     themselves
    0.11
    ãģĿãĤĮãģŀãĤĮ
    0.11
    åĪĨåĪ«ä¸º
    0.10
    ê°ģ
    0.09
    åĪĨåĪ¥
    0.09
    åĪĨåĪ«æĺ¯
    0.09
    ende
    0.09
    Activations Density 0.235%

    No Known Activations