© 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. 4999
    Prev
    Next
    INDEX
    Explanations

    enjoy the

    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
    _resolve
    -0.10
    åĬŀ好
    -0.10
    æĦŁæĥħ
    -0.09
    ùng
    -0.09
    穷人
    -0.09
    ä¹ĥèĩ³
    -0.09
    æĢĿ念
    -0.09
    ornado
    -0.09
     diamonds
    -0.09
     нелÑĮзÑı
    -0.09
    POSITIVE LOGITS
     either
    0.09
    ably
    0.09
    ances
    0.08
    either
    0.08
     bill
    0.08
    åĬ
    0.08
     ng
    0.08
    æµģè¡Į
    0.08
     Either
    0.08
     stab
    0.08
    Activations Density 0.016%

    No Known Activations