© 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. 2906
    Prev
    Next
    INDEX
    Explanations

    cost-effective solutions

    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
     scenes
    -0.26
    ä»ħ代表
    -0.25
     strongest
    -0.23
    sing
    -0.23
    è¡Į人
    -0.22
    èĥ¸åı£
    -0.22
    æ°ĶåĬ¿
    -0.22
     richest
    -0.22
    isplay
    -0.22
     fists
    -0.22
    POSITIVE LOGITS
     cost
    0.52
    æĪIJæľ¬
    0.51
    -cost
    0.50
    cost
    0.47
     costs
    0.45
    .cost
    0.45
    èĬĤ约
    0.43
    (cost
    0.43
    çļĦæĪIJæľ¬
    0.41
    æķĪçĽĬ
    0.40
    Activations Density 0.053%

    No Known Activations