© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36507
    Prev
    Next
    INDEX
    Explanations

    same-sex marriage

    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
    StateChanged
    -0.10
    æĶ¶åĪ°äºĨ
    -0.10
    upal
    -0.09
    è§ģè¯Ĩ
    -0.09
    ç´łé£Ł
    -0.09
    ifen
    -0.08
    yd
    -0.08
     vụ
    -0.08
    .collect
    -0.08
    æĶ¶åĪ°
    -0.08
    POSITIVE LOGITS
    енно
    0.09
    .appspot
    0.08
    ocop
    0.08
    ellig
    0.08
    .setFocus
    0.08
    çIJ¨
    0.08
    istik
    0.08
    à¸ķำ
    0.08
    åĩºåľº
    0.08
     Cong
    0.08
    Activations Density 0.033%

    No Known Activations