© 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. 452
    Prev
    Next
    INDEX
    Explanations

    anaerobic-oxic

    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
    åij½
    -0.24
     маÑı
    -0.22
    edException
    -0.22
    æ¡Ģ
    -0.22
    æľĢ大çļĦ
    -0.21
    è½½
    -0.20
     disp
    -0.20
     conv
    -0.20
     administration
    -0.20
    idd
    -0.19
    POSITIVE LOGITS
     fermentation
    0.27
    çĹ¢
    0.25
    å¤įä»ĩ
    0.25
    éĵ¡
    0.24
     hydrogen
    0.24
    çݯå¢ĥä¸ĭ
    0.24
     bacteria
    0.24
    oxic
    0.23
     digestion
    0.23
    archy
    0.22
    Activations Density 0.088%

    No Known Activations