© 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. 1836
    Prev
    Next
    INDEX
    Explanations

    like from a or some

    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
    麾
    -0.23
     Suites
    -0.23
    èģĮåĬ¡
    -0.22
     RESP
    -0.22
     reliance
    -0.22
    aning
    -0.22
    OVE
    -0.21
    åĿļ
    -0.21
     займ
    -0.21
    åħ¹
    -0.21
    POSITIVE LOGITS
     surreal
    0.33
    ç§ijå¹»
    0.29
    æ¼Ķ
    0.26
     nightmare
    0.25
    ä¼¼
    0.24
     Seriously
    0.24
     fiction
    0.24
    å¤įåı¤
    0.24
    æķħäºĭ
    0.23
    å°ı说
    0.23
    Activations Density 0.028%

    No Known Activations