© 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. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 470
    Prev
    Next
    INDEX
    Explanations

    publication and research

    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
    çħ¤æ°Ķ
    -0.28
     mouth
    -0.28
    æ²»å®ī
    -0.28
    éģĵåħ·
    -0.27
    失è°ĥ
    -0.27
    åĬ¨ä½ľ
    -0.26
    åľ°æĿ¿
    -0.26
    åij¨åħŃ
    -0.25
     gust
    -0.25
     suction
    -0.25
    POSITIVE LOGITS
     publishing
    0.48
    åĩºçīĪ
    0.47
     publication
    0.46
    publish
    0.45
     publish
    0.43
     publications
    0.42
     Publish
    0.41
    -publish
    0.41
    publication
    0.40
     publishers
    0.40
    Activations Density 0.030%

    No Known Activations