© 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. 636
    Prev
    Next
    INDEX
    Explanations

    area and land size units

    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
    ibri
    -0.27
     breakthrough
    -0.24
    æ°¨éħ¸
    -0.24
    Fuse
    -0.24
    ä¸įåIJĮç¨ĭ度
    -0.23
    æĸ°äº§åĵģ
    -0.23
    ÃľR
    -0.23
    bows
    -0.22
    éĥ
    -0.22
     Freak
    -0.22
    POSITIVE LOGITS
    éĿ¢ç§¯
    0.63
    æĢ»éĿ¢ç§¯
    0.59
     hectares
    0.55
     acres
    0.52
    éĿ¢ç§¯çº¦
    0.49
    å¹³æĸ¹ç±³
    0.48
    åħ¬é¡·
    0.48
    åįłåľ°
    0.47
    åįłåľ°éĿ¢ç§¯
    0.47
     acre
    0.47
    Activations Density 0.039%

    No Known Activations