© 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. 3017
    Prev
    Next
    INDEX
    Explanations

    before or after the

    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
     Proud
    -0.23
    -talk
    -0.23
    举åĬŀäºĨ
    -0.23
    åIJįçīĩ
    -0.22
    è¸Ķ
    -0.22
    æķ´æķ´
    -0.21
     ASAP
    -0.21
    quotes
    -0.21
    建设åĴĮ
    -0.21
     sant
    -0.21
    POSITIVE LOGITS
    çŃīåĽłç´ł
    0.40
    æľ¬èº«
    0.35
    èĩªèº«çļĦ
    0.35
    æľ¬èº«çļĦ
    0.35
    èĩªèº«
    0.33
     locality
    0.31
    æīĢåľ¨
    0.31
     season
    0.31
    åŃ£èĬĤ
    0.30
     itself
    0.30
    Activations Density 0.137%

    No Known Activations