© 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. 3366
    Prev
    Next
    INDEX
    Explanations

    law or rule

    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
    Negative Logits
    Trail
    -0.22
     flurry
    -0.22
    èĻij
    -0.22
     Trails
    -0.22
     aggress
    -0.22
     camp
    -0.22
    done
    -0.22
     mention
    -0.22
     Surveillance
    -0.22
     trail
    -0.22
    POSITIVE LOGITS
    å®ļå¾ĭ
    0.59
    è§Ħå¾ĭ
    0.59
    æ³ķåĪĻ
    0.54
    è§ĦåĪĻ
    0.49
     rules
    0.49
     laws
    0.49
    /rules
    0.44
     rule
    0.44
    .rule
    0.42
    (rule
    0.41
    Activations Density 0.059%

    No Known Activations