© 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. 7594
    Prev
    Next
    INDEX
    Explanations

    boating and sea navigation

    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
    .aspect
    -0.10
    èĪ¹
    -0.09
    èĭĩ
    -0.09
    èĪŁ
    -0.08
    ÑĩаÑĤ
    -0.08
    ủng
    -0.08
    èĪ¹èĪ¶
    -0.08
    woman
    -0.08
    æµĶ
    -0.08
     sail
    -0.08
    POSITIVE LOGITS
    åļ¼
    0.10
    æĪıåī§
    0.10
    å¼ĢçĽĺ
    0.09
    åı¯æĥ³
    0.09
    åī§çĥĪ
    0.09
    使人
    0.09
    èĪĴå¿ĥ
    0.09
    æĹłå½¢
    0.09
    çĶľèľľ
    0.09
    æŃ£æĸĩ
    0.09
    Activations Density 0.124%

    No Known Activations