© 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. 2639
    Prev
    Next
    INDEX
    Explanations

    digit or special character

    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
     cot
    -0.25
    KHR
    -0.24
     tern
    -0.24
    åī²
    -0.23
    sq
    -0.23
    RIX
    -0.23
     denomin
    -0.22
    èģĶåIJĪä¼ļ
    -0.21
    AT
    -0.21
    Printf
    -0.21
    POSITIVE LOGITS
     uncert
    0.24
    å¼Ł
    0.22
    .Clone
    0.22
    citation
    0.22
     adverts
    0.21
    already
    0.21
    opathy
    0.21
     Authenticate
    0.21
    颤æĬĸ
    0.21
    å¸ĥæľĹ
    0.21
    Activations Density 0.031%

    No Known Activations