© 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. 1675
    Prev
    Next
    INDEX
    Explanations

    brave or bravery

    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
    weet
    -0.09
    overe
    -0.09
    owe
    -0.09
    ene
    -0.08
    çĸ
    -0.08
    ừng
    -0.08
    è¿Ļå°±
    -0.08
    رات
    -0.08
    å¼ķåĬĽ
    -0.08
    ãĤº
    -0.08
    POSITIVE LOGITS
    åĭĩæķ¢
    0.10
     brav
    0.10
    åĭĩæ°Ķ
    0.09
    CBS
    0.09
    anden
    0.09
     дÑĥÑħ
    0.09
    éĢļéģĵ
    0.09
    IOR
    0.09
    æ£ķèī²
    0.09
    å®ķ
    0.09
    Activations Density 0.015%

    No Known Activations