© 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. 55817
    Prev
    Next
    INDEX
    Explanations

    assistance programs or benefits

    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
    poster
    -0.09
    NA
    -0.09
    åIJĦæĸ¹
    -0.09
    afil
    -0.08
     dismissing
    -0.08
    éĻIJå®ļ
    -0.08
    nsic
    -0.08
    çĥ¦
    -0.08
    é«ĺåľ°
    -0.08
    /Foundation
    -0.08
    POSITIVE LOGITS
    æ¾
    0.08
    涿
    0.08
    æµı
    0.08
    æľīäºĨ
    0.08
    oup
    0.08
    æĸ°é²ľ
    0.08
    å±ħæ°ij
    0.08
    allowed
    0.08
    arian
    0.08
    iloc
    0.08
    Activations Density 0.003%

    No Known Activations