© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 478
    Prev
    Next
    INDEX
    Explanations

    draw or drawback related terms

    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
    apro
    -0.22
    çĦ¦
    -0.21
     drink
    -0.20
    饮æĸĻ
    -0.20
     Beckham
    -0.20
    -0.20
    çĤ¬
    -0.20
    ocus
    -0.19
    upp
    -0.19
    CUS
    -0.19
    POSITIVE LOGITS
    äºĶéĩij
    0.26
    boat
    0.24
     dresser
    0.23
    /tab
    0.22
    车åºĵ
    0.21
    /socket
    0.21
    /column
    0.21
    tiny
    0.20
    lin
    0.20
    lain
    0.20
    Activations Density 0.006%

    No Known Activations