© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37094
    Prev
    Next
    INDEX
    Explanations

    waters: surrounding, in, near, of

    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
    ITY
    -0.10
    åı¯è§Ĩ
    -0.09
    æĸ¯åŁº
    -0.09
    erva
    -0.09
    ein
    -0.09
    smith
    -0.09
    äºĨä¸Ģåı¥
    -0.09
    åľ©
    -0.09
    åĶı
    -0.08
    ity
    -0.08
    POSITIVE LOGITS
    ãģ£ãģįãĤĬ
    0.10
    人éĢł
    0.10
    rant
    0.10
    urance
    0.09
    ound
    0.09
    uth
    0.09
    forth
    0.09
    idon
    0.09
     ÑģовеÑĢÑĪен
    0.09
    úde
    0.09
    Activations Density 0.020%

    No Known Activations