© 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. 2921
    Prev
    Next
    INDEX
    Explanations

    colored descriptors and foods

    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
    éĤ¶
    -0.24
    holm
    -0.23
    iders
    -0.23
    лив
    -0.23
    èı½
    -0.22
     jeep
    -0.22
     township
    -0.22
    UEL
    -0.22
    鸱
    -0.21
     BATCH
    -0.21
    POSITIVE LOGITS
    æĪĸ
    0.29
    端æŃ£
    0.29
    æĪĸå¤ļ
    0.28
     or
    0.26
    æıŃ
    0.25
    çĵľ
    0.25
    åįij
    0.23
     colored
    0.23
     peppers
    0.23
    ç¿»è¯ij
    0.23
    Activations Density 0.001%

    No Known Activations