© 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. 4437
    Prev
    Next
    INDEX
    Explanations

    Israeli military, intelligence, army

    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
    å¸ĥç½®
    -0.09
    ä¸IJ
    -0.09
    æĦļ
    -0.09
    å¤ļåľ°
    -0.09
    ether
    -0.09
    æ·Ģ
    -0.09
     reform
    -0.08
    /value
    -0.08
    æĹ¥å¸¸å·¥ä½ľ
    -0.08
    ocal
    -0.08
    POSITIVE LOGITS
    以èī²åĪĹ
    0.15
     Israeli
    0.12
    Israeli
    0.12
     Netanyahu
    0.11
     IDF
    0.10
    Israel
    0.10
     Israel
    0.10
     Aviv
    0.09
     Israelis
    0.09
    é²ģ
    0.09
    Activations Density 0.066%

    No Known Activations