© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-8B
    5. 18-RESID-BATCHTOPK-65K__L0-80
    7. 794
    Prev
    Next
    INDEX
    Explanations

    questions about numbers and days

    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
    çĶļèĩ³
    -0.28
    åİŁåŀĭ
    -0.27
    çĶļèĩ³æĺ¯
    -0.27
    çĶļèĩ³è¿ĺ
    -0.26
    è¿ijä¹İ
    -0.26
    (sprintf
    -0.25
    åľ°çIJĥä¸Ĭ
    -0.25
     tháºŃm
    -0.25
     roughly
    -0.25
     broadly
    -0.25
    POSITIVE LOGITS
    æľ¬æĬ¥è®¯
    0.27
    注éĶĢ
    0.26
    æľ¬åij¨
    0.26
     surname
    0.25
     Monday
    0.24
     weekdays
    0.24
    æľ¬æľĪ
    0.24
     Deletes
    0.24
    ToDelete
    0.24
    åĪłéĻ¤æĪIJåĬŁ
    0.24
    Activations Density 0.033%

    No Known Activations