© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    marketing and advertising materials

    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
    .compute
    -0.27
    .abort
    -0.25
     exacerbated
    -0.25
    MainThread
    -0.25
     malformed
    -0.25
    ç¥
    -0.24
    reserve
    -0.24
    å°ıæŶåīį
    -0.23
    ç»ĿæľĽ
    -0.23
    Abort
    -0.23
    POSITIVE LOGITS
    è½½ä½ĵ
    0.46
    æķĪæŀľ
    0.39
    èĢIJçĶ¨
    0.38
    åĵģçīĮ形象
    0.38
     branding
    0.37
     ROI
    0.36
    vertising
    0.36
    æĬķæĶ¾
    0.36
     visually
    0.34
    å±ķ示
    0.34
    Activations Density 0.066%

    No Known Activations