© 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. 3357
    Prev
    Next
    INDEX
    Explanations

    wage and archives

    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
    mons
    -0.24
    æĭĽçĶŁ
    -0.23
    åĬ¿åĬĽ
    -0.22
    czy
    -0.22
    abler
    -0.21
     Prescott
    -0.21
    vern
    -0.21
    lij
    -0.21
    bras
    -0.21
    si
    -0.21
    POSITIVE LOGITS
     flushing
    0.25
     scram
    0.24
    exion
    0.23
     postfix
    0.22
    ioned
    0.22
    opup
    0.21
    /AP
    0.21
     drip
    0.21
    åį´è¢«
    0.21
    精确
    0.21
    Activations Density 0.003%

    No Known Activations