© 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. 30305
    Prev
    Next
    INDEX
    Explanations

    plea or plead

    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
    稳
    -0.08
     lÃłnh
    -0.08
    bie
    -0.08
    ä¸Ģè¶Ł
    -0.08
    arb
    -0.07
     regard
    -0.07
    bon
    -0.07
    âĸ¼
    -0.07
     lÃŃder
    -0.07
    åĦ¿
    -0.07
    POSITIVE LOGITS
    undry
    0.11
    ä¸įæ¸ħ
    0.11
    iane
    0.10
    /respond
    0.10
    çļĦæĹ¥åŃIJéĩĮ
    0.10
    ÑĪив
    0.10
     rằng
    0.10
    enta
    0.10
    sing
    0.10
    URE
    0.09
    Activations Density 0.005%

    No Known Activations