© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20312
    Prev
    Next
    INDEX
    Explanations

    bombing during attacks

    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
    ä¸Ģ头
    -0.12
    æºľ
    -0.09
    æłħ
    -0.09
    æľįåĬ¡åĮº
    -0.09
    åĨĴéĻ©
    -0.09
    ä»ĭåħ¥
    -0.08
    elsen
    -0.08
    å¥Ī
    -0.08
    antar
    -0.08
    èij£äºĭ
    -0.08
    POSITIVE LOGITS
    è½°çĤ¸
    0.15
    çĤ¸
    0.15
    çĤ¸å¼¹
    0.14
    blast
    0.13
     blast
    0.12
     bombing
    0.12
     bomb
    0.12
    糸
    0.11
    æł¸
    0.11
    çĪĨçĤ¸
    0.10
    Activations Density 0.135%

    No Known Activations