© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 3115
    Prev
    Next
    INDEX
    Explanations

    observed phenomenon or trend

    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
    åħ¨æµģç¨ĭ
    -0.34
    æĮīè§Ħå®ļ
    -0.31
    éĢļåħ³
    -0.30
    æī¿è¯º
    -0.28
     instructions
    -0.28
    èªĵ
    -0.27
    å®īåħ¨ä¿Ŀéļľ
    -0.27
    æķijæĬ¤è½¦
    -0.27
    æķijæı´
    -0.27
     authorized
    -0.27
    POSITIVE LOGITS
     trends
    0.44
    çݰ象
    0.43
    çļĦçݰ象
    0.42
     Trends
    0.40
     phenomenon
    0.40
    è¶ĭåĬ¿
    0.40
    çļĦè¶ĭåĬ¿
    0.40
     phenomena
    0.39
     trend
    0.38
    æĻ®éģį
    0.38
    Activations Density 0.110%

    No Known Activations