© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 2064
    Prev
    Next
    INDEX
    Explanations

    your / yours followed by noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-8b-saes/saes_Qwen_Qwen3-8B_batch_top_k/resid_post_layer_18
    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
    HN
    -0.26
    çļĦåĬªåĬĽ
    -0.24
    é£İæ°Ķ
    -0.24
    åģļäºĭ
    -0.24
    ä½ľé£İ
    -0.23
     studios
    -0.23
    èĦijåŃIJéĩĮ
    -0.23
    çĶŁæ´»ä¹łæĥ¯
    -0.23
    å©Ĩå©Ĩ
    -0.23
    æĹ¥å¸¸å·¥ä½ľ
    -0.22
    POSITIVE LOGITS
     soon
    0.29
     qualifying
    0.27
    æĸ°çļĦ
    0.25
     eventually
    0.24
     finalized
    0.24
     candidate
    0.24
    èµ·ä¹ī
    0.24
    åı·
    0.24
     candidates
    0.24
    æĪĸå¤ļ
    0.24
    Activations Density 0.031%

    No Known Activations