© 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. 3127
    Prev
    Next
    INDEX
    Explanations

    miles, hours, workload, units

    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
    thon
    -0.23
    æĭ¾
    -0.23
    åĶ§
    -0.23
    ÑģÑĤвеннÑĭе
    -0.22
     gri
    -0.22
    elman
    -0.22
    èļģ
    -0.22
    èĤłéģĵ
    -0.22
    æĪijèĥ½
    -0.22
    ä¸ĢæĬĬ
    -0.21
    POSITIVE LOGITS
     Warranty
    0.25
    éĩĮç¨ĭ
    0.25
     conditions
    0.24
    .rmi
    0.23
    误åĮº
    0.23
    éĺĪ
    0.23
    ä¸ĩåħ¬éĩĮ
    0.23
     Fiat
    0.23
     limits
    0.22
    éĩĮç¨ĭç¢ij
    0.22
    Activations Density 0.022%

    No Known Activations