© 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. 61528
    Prev
    Next
    INDEX
    Explanations

    transportation and related officials

    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
    ä½ıæĪ·
    -0.10
    涧
    -0.10
    å¡«åħħ
    -0.10
    ernet
    -0.10
    iore
    -0.10
    ä¸ŃåĽ½ç»ıæµİ
    -0.09
    离åİ»
    -0.09
    ç¨Ķ
    -0.09
    ä¸ĢæľŁ
    -0.09
    ibel
    -0.09
    POSITIVE LOGITS
     passenger
    0.10
    客è¿IJ
    0.09
    اد
    0.09
     Passenger
    0.09
    amas
    0.08
     accident
    0.08
    继
    0.08
    ious
    0.08
    å²IJ
    0.08
     cand
    0.08
    Activations Density 0.033%

    No Known Activations