© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15371
    Prev
    Next
    INDEX
    Explanations

    Israel and Israeli entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Maul
    -0.22
    éĴī
    -0.22
    衬
    -0.21
     Iowa
    -0.21
    ç®Ģ
    -0.20
    æ»ģ
    -0.20
    ä¿¡èªī
    -0.20
     Michigan
    -0.20
    äºijåįĹ
    -0.20
     undead
    -0.20
    POSITIVE LOGITS
     Israeli
    0.48
    以èī²åĪĹ
    0.47
    Israeli
    0.44
     Israel
    0.42
     Netanyahu
    0.42
     Israelis
    0.41
    Israel
    0.39
    -Israel
    0.38
     Aviv
    0.35
     Hebrew
    0.34
    Activations Density 0.208%

    No Known Activations