© 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. 1443
    Prev
    Next
    INDEX
    Explanations

    who followed by question words

    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
    -0.29
    quired
    -0.25
    æİĩ
    -0.21
    ted
    -0.20
    mente
    -0.20
    Illegal
    -0.19
    è®¤çľŁåŃ¦ä¹ł
    -0.19
    ä¸ĢåĪĩéĥ½
    -0.18
     situ
    -0.18
    æģ¶åĬ£
    -0.18
    POSITIVE LOGITS
    æł·çļĦ
    0.30
     else
    0.29
    soever
    0.28
    /how
    0.28
    else
    0.28
    craft
    0.23
     же
    0.23
    -ever
    0.23
    erer
    0.23
    oley
    0.23
    Activations Density 0.027%

    No Known Activations