© 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. 27966
    Prev
    Next
    INDEX
    Explanations

    immigration, migration, fraud, society

    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
    é«ĺåľ°
    -0.09
    éĵ
    -0.09
     mature
    -0.09
    .asset
    -0.09
    asset
    -0.09
    娱
    -0.09
    ogan
    -0.08
    Asset
    -0.08
     Twin
    -0.08
    Synopsis
    -0.08
    POSITIVE LOGITS
     hol
    0.11
    éľį
    0.10
    éĢłæĪIJ
    0.10
    纯æ´ģ
    0.10
    é¡·
    0.09
    åĩĢ
    0.09
     Hol
    0.09
     dil
    0.09
    åĩĮ
    0.09
    æݥ管
    0.09
    Activations Density 0.087%

    No Known Activations