© 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. 51101
    Prev
    Next
    INDEX
    Explanations

    sea related words

    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
    gable
    -0.09
    leur
    -0.09
    趾
    -0.09
    opher
    -0.09
    oire
    -0.09
    oplan
    -0.09
    è¾Ī
    -0.08
    ÅĦski
    -0.08
    çľĭæ¸ħ
    -0.08
    /topics
    -0.08
    POSITIVE LOGITS
    鸥
    0.10
    涯
    0.10
    око
    0.09
    åIJİå¤ĩ
    0.09
    ly
    0.09
    æ·¡åĮĸ
    0.09
    æ½®
    0.08
    漫æŃ¥
    0.08
    è¿¢
    0.08
    าะ
    0.08
    Activations Density 0.011%

    No Known Activations