© 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. 1442
    Prev
    Next
    INDEX
    Explanations

    species of trees and plants

    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
     миÑĢов
    -0.29
    æĹħç¨ĭ
    -0.27
     rant
    -0.26
    浯
    -0.25
    magic
    -0.25
    å®ŀè·µä¸Ń
    -0.25
    æµģåĩº
    -0.25
     geek
    -0.24
     meddling
    -0.24
    åıijå±ķä¸Ń
    -0.24
    POSITIVE LOGITS
    éĤĦæľī
    0.28
    çŃīä¸Ģæī¹
    0.26
    以åıĬåħ¶ä»ĸ
    0.26
     clusters
    0.25
     species
    0.25
     occasionally
    0.24
     woodland
    0.24
    elong
    0.23
     sometimes
    0.23
     thick
    0.23
    Activations Density 0.033%

    No Known Activations