© 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. 51108
    Prev
    Next
    INDEX
    Explanations

    territorial disputes and claims

    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
    åij¨è½¬
    -0.10
    ä¸Ģ个个
    -0.10
    æĬķ身
    -0.08
    楼ä¸ĭ
    -0.08
    èIJij
    -0.08
    ä½ıåľ¨
    -0.08
     narrowly
    -0.08
    .tap
    -0.08
     dá»ĭp
    -0.08
    ç´§ç´§åĽ´ç»ķ
    -0.08
    POSITIVE LOGITS
     disputed
    0.12
    çķĮ
    0.12
     claim
    0.11
    åĪĨåī²
    0.11
    äºīè®®
    0.11
    è¾¹çķĮ
    0.10
    åĪĴ
    0.10
    çĿ¦
    0.10
    åįłæľī
    0.10
    çķĮéĻIJ
    0.10
    Activations Density 0.068%

    No Known Activations