© 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. 38246
    Prev
    Next
    INDEX
    Explanations

    smells of substances and things

    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
    åĻªéŁ³
    -0.11
    çľ¼çIJĥ
    -0.10
    å£°éŁ³
    -0.10
    ä¹IJ趣
    -0.10
    ç¬ij声
    -0.10
    é³³
    -0.09
    æĬĢ
    -0.09
    é¢Īæ¤İ
    -0.09
    éķĵ
    -0.09
    纳æĸ¯
    -0.09
    POSITIVE LOGITS
     observ
    0.09
     пÑĢоизведен
    0.09
    å¼ĢåѦ
    0.09
    çĶĺ
    0.08
     damp
    0.08
    æģĴ
    0.08
    observ
    0.08
     freshly
    0.08
    å·²ä¹ħ
    0.08
    åĹħ
    0.08
    Activations Density 0.043%

    No Known Activations