© 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. 2598
    Prev
    Next
    INDEX
    Explanations

    Getty Images

    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
     charms
    -0.25
    apon
    -0.24
    émon
    -0.23
    apan
    -0.23
    erset
    -0.23
    eltas
    -0.23
    sel
    -0.22
     blunt
    -0.21
    .removeListener
    -0.21
     horm
    -0.21
    POSITIVE LOGITS
    Buf
    0.24
     eq
    0.23
    è°ħ解
    0.23
    pane
    0.22
     (_,
    0.22
     (“
    0.22
    VES
    0.22
    [,]
    0.21
     Bust
    0.20
    æĪŁ
    0.20
    Activations Density 0.009%

    No Known Activations