© 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. 61448
    Prev
    Next
    INDEX
    Explanations

    immigrant policy and status

    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
    移æ°ij
    -0.13
     immigration
    -0.10
    éļ¾æ°ij
    -0.09
    üb
    -0.09
    趣
    -0.09
    éļľ
    -0.09
    .native
    -0.09
     Immigration
    -0.09
    ç§įæĹı
    -0.09
     refugee
    -0.08
    POSITIVE LOGITS
     vig
    0.10
    orsk
    0.10
    线ä¸ĭ
    0.09
    ILED
    0.09
     Byrne
    0.09
    æĬ«
    0.09
    ilenames
    0.09
    æľīæľĽ
    0.09
    _STA
    0.08
    åįģä½Ļå¹´
    0.08
    Activations Density 0.019%

    No Known Activations