© 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. 32823
    Prev
    Next
    INDEX
    Explanations

    Syrian refugees

    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
     scare
    -0.10
    åīľ
    -0.10
    衬
    -0.10
     гаÑĢ
    -0.09
    _REST
    -0.09
    arResult
    -0.09
    æļ´
    -0.09
    çĹķ
    -0.08
    æ·±å¤ľ
    -0.08
    è°IJ
    -0.08
    POSITIVE LOGITS
    maids
    0.09
    _managed
    0.09
    éļ¾æ°ij
    0.09
    妥åĸĦ
    0.09
    orp
    0.09
    eten
    0.09
    庵
    0.09
    åľ¨å¤ĸéĿ¢
    0.09
    verse
    0.09
    aky
    0.08
    Activations Density 0.085%

    No Known Activations