© 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. 742
    Prev
    Next
    INDEX
    Explanations

    slowly followed by verbs

    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
     easily
    -0.25
     briefly
    -0.25
     frequently
    -0.24
    oir
    -0.23
    brief
    -0.23
    Brief
    -0.22
     Brief
    -0.21
    ois
    -0.21
     brief
    -0.21
    ä»ħä»ħæĺ¯
    -0.21
    POSITIVE LOGITS
    æħ¢æħ¢
    0.44
     slowly
    0.44
     dần
    0.43
    éĢIJæ¸IJ
    0.42
    æħ¢æħ¢åľ°
    0.41
    éĢIJæŃ¥
    0.40
    æ¸IJ
    0.37
     gradually
    0.36
    ç¼ĵæħ¢
    0.36
    æħ¢æħ¢çļĦ
    0.35
    Activations Density 0.022%

    No Known Activations