© 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. 1641
    Prev
    Next
    INDEX
    Explanations

    motivated Mars, structure, Julian, <?php

    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
    tin
    -0.28
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.28
    äºĶçĻ¾
    -0.27
    åĨĻçĿĢ
    -0.27
    åħ¨è¦ĨçĽĸ
    -0.27
    âĢ½
    -0.26
    溯æºIJ
    -0.26
    åľ¨ä¸ŃåĽ½
    -0.26
     hundreds
    -0.26
    è´Ń票
    -0.26
    POSITIVE LOGITS
     sensual
    0.31
     feelings
    0.28
     intros
    0.27
    qualities
    0.27
     psychic
    0.26
     emotions
    0.25
     desires
    0.25
     Prostit
    0.25
     emotional
    0.24
    æĺ¯ä½ł
    0.24
    Activations Density 0.014%

    No Known Activations