© 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. 1925
    Prev
    Next
    INDEX
    Explanations

    directory paths

    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
    anni
    -0.28
    çĶŁæ´»åľ¨
    -0.23
     trib
    -0.23
     Tumblr
    -0.22
    .NET
    -0.22
    annes
    -0.22
     Trib
    -0.21
     amateur
    -0.21
     tribes
    -0.21
    æĹ¥ä¸ĭåįĪ
    -0.21
    POSITIVE LOGITS
    -files
    0.27
    以åıĬåħ¶ä»ĸ
    0.23
    åħ¨å±Ģ
    0.23
    raries
    0.22
    æĪĸåħ¶ä»ĸ
    0.21
    çŃīéĥ¨éŨ
    0.21
     FileName
    0.21
    两级
    0.21
     files
    0.21
    _redirected
    0.21
    Activations Density 0.489%

    No Known Activations