© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    sale and demand

    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
    ç¬ij声
    -0.09
    å¹½é»ĺ
    -0.09
    Gam
    -0.09
    wat
    -0.09
    对èĩªå·±çļĦ
    -0.08
    æŁ¥çľĭæĽ´å¤ļ
    -0.08
    å£°éŁ³
    -0.08
    à¸Ĺร
    -0.08
     Ø£Ùħ
    -0.08
    æĥ³åĪ°äºĨ
    -0.08
    POSITIVE LOGITS
    å¸ĤåľºéľĢæ±Ĥ
    0.12
    ç»Ī
    0.11
    æ¶Īè´¹éľĢæ±Ĥ
    0.10
    åħ¨åĽ½äººæ°ij
    0.10
     destinations
    0.10
    å¸Ĥåľº
    0.10
    æ¶Īè´¹èĢħ
    0.10
    缮çļĦåľ°
    0.09
    æ¶Īè´¹
    0.09
     destino
    0.09
    Activations Density 0.119%

    No Known Activations