© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 902
    Prev
    Next
    INDEX
    Explanations

    Israel, Israeli, Hebrew, Netanyahu

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    è´µå·ŀçľģ
    -0.31
     ASTM
    -0.27
    è´µå·ŀ
    -0.27
     Tacoma
    -0.26
    تأسÙĬ
    -0.26
    ä¾Ĺ
    -0.26
     Mississippi
    -0.26
     Louisiana
    -0.25
     Winchester
    -0.25
    å²ľ
    -0.24
    POSITIVE LOGITS
    以èī²åĪĹ
    0.68
     Israeli
    0.64
     Israel
    0.57
    Israeli
    0.57
    Israel
    0.56
     Israelis
    0.54
    -Israel
    0.52
     Netanyahu
    0.52
     Zionist
    0.50
     Hebrew
    0.49
    Activations Density 0.158%

    No Known Activations