© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 144
    Prev
    Next
    INDEX
    Explanations

    Columbus Day

    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
     vener
    -0.23
     Bite
    -0.23
     compliment
    -0.23
     wor
    -0.23
     Brush
    -0.22
    èĬ
    -0.22
    å¥
    -0.22
     cus
    -0.21
     unrelated
    -0.21
     unlocks
    -0.21
    POSITIVE LOGITS
    ether
    0.23
    梯
    0.22
    finger
    0.22
    åĤ¬åĮĸåīĤ
    0.22
    father
    0.22
    ufs
    0.22
    flo
    0.22
    prompt
    0.22
    chem
    0.22
    pagination
    0.22
    Activations Density 0.004%

    No Known Activations