© 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. 39110
    Prev
    Next
    INDEX
    Explanations

    celestial bodies and space

    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¥ī
    -0.10
    èīĦ
    -0.09
    åĸī
    -0.09
    çļ¤
    -0.09
    åĩ«
    -0.09
    æľ¬æľŁ
    -0.09
    è°ħ
    -0.09
    ylum
    -0.09
    é¢Īéĥ¨
    -0.08
    å¨ģåĬĽ
    -0.08
    POSITIVE LOGITS
    çģ«æĺŁ
    0.13
     mars
    0.11
     Mars
    0.11
    åľ¨åĽ½å¤ĸ
    0.10
    åĽ½å¤ĸ
    0.10
    å¤ĸåľ°
    0.10
    åľ¨å¤ĸ
    0.10
     abroad
    0.10
    åľ°çIJĥ
    0.09
    æĺŁçIJĥ
    0.09
    Activations Density 0.066%

    No Known Activations