© 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. 1640
    Prev
    Next
    INDEX
    Explanations

    maintained, persists, constant, powered, monotonic

    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
     Bund
    -0.27
     Lynn
    -0.23
    宣å¸ĥ
    -0.22
    åĽĽçº§
    -0.21
    terr
    -0.21
     Pistol
    -0.21
    亲
    -0.21
    åµĮ
    -0.21
    æŀģ度
    -0.21
     nal
    -0.21
    POSITIVE LOGITS
    less
    0.29
    æĪĸå¤ļæĪĸå°ij
    0.27
     ìĺ¤íŀĪ볤
    0.25
    åıįèĢĮ
    0.24
    ä¸ĢåĪĢ
    0.23
    igue
    0.22
    ub
    0.22
    ölü
    0.21
    æħĬ
    0.21
     tm
    0.21
    Activations Density 0.321%

    No Known Activations