© 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. 10929
    Prev
    Next
    INDEX
    Explanations

    Nobel Prize, Award for winning

    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
    itty
    -0.08
    aven
    -0.08
    iles
    -0.08
    åħīèį£
    -0.08
    å¤ĸåĽ½äºº
    -0.08
    ILES
    -0.08
    icz
    -0.08
    ÑıÑĤи
    -0.08
     Ronald
    -0.07
    åij
    -0.07
    POSITIVE LOGITS
    çľŁç©º
    0.11
    å°ĺ
    0.10
    æĸĽ
    0.10
    anel
    0.09
     sidel
    0.09
    bid
    0.09
    æĹ¥å¸¸å·¥ä½ľ
    0.09
     bid
    0.09
     Bid
    0.09
    ä¸Ģ身
    0.09
    Activations Density 0.052%

    No Known Activations