© 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. 9684
    Prev
    Next
    INDEX
    Explanations

    time and weather references

    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
    èĢIJ
    -0.10
    æ´¼
    -0.10
    éŃģ
    -0.09
    ç»ĵæŀĦæĢ§
    -0.09
    解读
    -0.09
    geber
    -0.09
    intree
    -0.09
    æ®ĥ
    -0.09
    è¿Ļéĥ¨åĪĨ
    -0.09
    _finder
    -0.08
    POSITIVE LOGITS
    æ¸ħæĻ¨
    0.10
    à¹ģà¸ĸ
    0.09
    æŁIJ个
    0.09
    æŁIJ
    0.08
    validated
    0.08
    ä¼ĺéĢī
    0.08
    å°±è¿Ļä¹Ī
    0.08
    没æľīä»»ä½ķ
    0.08
    æµĨ
    0.08
    ä¸ºä½ł
    0.08
    Activations Density 0.133%

    No Known Activations