© 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. 2140
    Prev
    Next
    INDEX
    Explanations

    about this, on the, for the

    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
    icter
    -0.28
    xDB
    -0.27
    fter
    -0.26
    iasi
    -0.26
    åħĪæĺ¯
    -0.25
     decay
    -0.24
    anes
    -0.23
    ichel
    -0.23
    è·Ŀ
    -0.23
    æĬij
    -0.23
    POSITIVE LOGITS
     Mention
    0.27
    æĤ¨çļĦ
    0.26
     ANY
    0.24
     Viol
    0.24
     Sponsored
    0.24
     Rece
    0.24
     Computers
    0.24
    æľ¬æ¡Ī
    0.24
     Bicycle
    0.24
     Stard
    0.24
    Activations Density 0.247%

    No Known Activations