© 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. 1029
    Prev
    Next
    INDEX
    Explanations

    bring along or with

    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
    è¿ĿèĥĮ
    -0.25
    ://%
    -0.24
    forder
    -0.24
    æĹłæķ°æ¬¡
    -0.23
    æ¯ı次
    -0.23
    ç»Īäºİ
    -0.23
    ynet
    -0.23
     mãi
    -0.23
    -syntax
    -0.23
    feeds
    -0.22
    POSITIVE LOGITS
    æIJºå¸¦
    0.30
    éĹ²ç½®
    0.27
    ä¹Łä¸įè¦ģ
    0.27
     participate
    0.27
     join
    0.27
    åĩĨå¤ĩ好
    0.27
    带ä¸Ĭ
    0.26
    èĩªå¸¦
    0.26
     optionally
    0.26
     NOTE
    0.26
    Activations Density 0.010%

    No Known Activations