© 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. 32606
    Prev
    Next
    INDEX
    Explanations

    explicit water

    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
    夺
    -0.09
    lez
    -0.09
    1
    -0.09
    çģ¶
    -0.09
    8
    -0.08
    0
    -0.08
    èĥŀ
    -0.08
    åĩĨåħ¥
    -0.08
    èĥİ
    -0.08
    5
    -0.08
    POSITIVE LOGITS
    æ°´èµĦæºIJ
    0.19
    æ°´éĩı
    0.18
     water
    0.18
    æ°´åĪĨ
    0.17
     водÑĭ
    0.17
    æ°´æºIJ
    0.16
    æ°´ä¸Ń
    0.16
    ä¾Ľæ°´
    0.16
     WATER
    0.15
    çĶ¨æ°´
    0.15
    Activations Density 0.129%

    No Known Activations