© 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. 35435
    Prev
    Next
    INDEX
    Explanations

    folding, collapsing, expanding

    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
    ä»ħ代表
    -0.10
     cent
    -0.09
    ä¸ĵ线
    -0.09
    审议
    -0.09
    ildo
    -0.08
    argon
    -0.08
    é¢ł
    -0.08
    ứt
    -0.08
    ActionCode
    -0.08
    éĻ¸
    -0.08
    POSITIVE LOGITS
    æĬĺåıł
    0.12
    éĽī
    0.11
    以便
    0.11
    æĸ¹ä¾¿
    0.10
     unfolded
    0.09
     Folding
    0.09
    å¾Īæĸ¹ä¾¿
    0.09
     folding
    0.09
    å±ķå¼Ģ
    0.09
    é¦ĸå¸Ń
    0.09
    Activations Density 0.207%

    No Known Activations