© 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. 1480
    Prev
    Next
    INDEX
    Explanations

    numbers and units of measurement

    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
    åŁĤ
    -0.23
    åĶ¯ä¸ĢçļĦ
    -0.23
    thed
    -0.23
    çĸı导
    -0.22
    /close
    -0.21
    &w
    -0.20
    çĶŁæĢķ
    -0.20
     fred
    -0.20
    红线
    -0.20
    å¸ĪçĶŁ
    -0.20
    POSITIVE LOGITS
    /reference
    0.23
     stat
    0.23
    CLI
    0.22
    æĹĹèĪ°
    0.22
     cricket
    0.22
    ELSE
    0.22
     vat
    0.21
    .stat
    0.21
    (reference
    0.21
     ELSE
    0.21
    Activations Density 0.081%

    No Known Activations