© 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. 1706
    Prev
    Next
    INDEX
    Explanations

    and or as

    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
    她æĺ¯
    -0.24
     Bergen
    -0.23
    ä»ĸ们æĺ¯
    -0.23
    exterity
    -0.21
    ä¸įä½Ĩ
    -0.21
    ä¸įä»ħèĥ½
    -0.21
    è½Ń
    -0.20
    ynes
    -0.20
    éļ¨èijĹ
    -0.20
    缺åı£
    -0.20
    POSITIVE LOGITS
    åħ¶å®ĥ
    0.28
     instrumental
    0.27
     other
    0.26
    neh
    0.24
    åºľ
    0.23
     //↵
    0.22
    客æĪ·éľĢæ±Ĥ
    0.21
     canned
    0.21
    人们çļĦ
    0.21
     alas
    0.21
    Activations Density 0.293%

    No Known Activations