© 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. 19696
    Prev
    Next
    INDEX
    Explanations

    communicating or presenting information

    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
     Peg
    -0.10
    bah
    -0.10
    çĽijæĬ¤
    -0.09
    éĢĭ
    -0.09
    æĻĶ
    -0.09
    é©·
    -0.09
    engo
    -0.09
     Revel
    -0.09
     Gon
    -0.09
    ä¸įå®Į
    -0.09
    POSITIVE LOGITS
    说æĪij
    0.11
    ä»İæł¹æľ¬
    0.09
    åįģ大
    0.08
    åı¯è§Ĥ
    0.08
    äºĴèģĶ
    0.08
    è¦ģä¹Ī
    0.08
    è¿Ļ件äºĭæĥħ
    0.08
    æµĵåİļ
    0.08
    å¥ij约
    0.08
     Jung
    0.08
    Activations Density 0.187%

    No Known Activations