© 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. 1513
    Prev
    Next
    INDEX
    Explanations

    single dose or exposure

    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
    AGED
    -0.26
     Lif
    -0.23
    (region
    -0.23
    æıĨ
    -0.23
    Region
    -0.23
     sph
    -0.22
    寿åij½
    -0.22
     region
    -0.22
     Hour
    -0.22
     Báo
    -0.22
    POSITIVE LOGITS
    ä¸Ģ次次
    0.53
    åĩłæ¬¡
    0.52
    æ¯ıä¸Ģ次
    0.52
    æ¯ı次
    0.51
    æ¯ı次éĥ½
    0.48
    ä¸Ģ次
    0.48
    æľīä¸Ģ次
    0.48
    æľĢåIJİä¸Ģ次
    0.47
    次æķ°
    0.45
    æ¯ıåij¨
    0.45
    Activations Density 0.381%

    No Known Activations