© 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. 48151
    Prev
    Next
    INDEX
    Explanations

    arrogance, haughty, oath

    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
    otte
    -0.10
    ings
    -0.10
    çļĦæĦŁæĥħ
    -0.10
    ric
    -0.09
    forme
    -0.09
    麹
    -0.09
    flix
    -0.09
    ssf
    -0.09
    ä½łå¥½
    -0.09
     обÑĭ
    -0.09
    POSITIVE LOGITS
     ea
    0.09
    ä½ĵ系建设
    0.09
    è¿ĻéĩĮæľī
    0.08
    ä¸įçIJĨ
    0.08
     desn
    0.08
    cg
    0.08
    ä¸ĭå±ŀ
    0.08
    /or
    0.08
    è°ģèĥ½
    0.08
    è£ħéħį
    0.08
    Activations Density 0.009%

    No Known Activations