© 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. 1940
    Prev
    Next
    INDEX
    Explanations

    's / was / is / can / should

    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
    åѤåĦ¿
    -0.22
    人çĶŁçļĦ
    -0.22
    ä»»ä½ķ人éĥ½
    -0.21
    ä»»ä½ķ人
    -0.21
    æĪIJ为ä¸Ģ个
    -0.21
     AIM
    -0.21
    æľī人
    -0.20
    WL
    -0.20
     apex
    -0.20
    ivic
    -0.20
    POSITIVE LOGITS
    们
    0.43
    è¿Ļ个èģĮä¸ļ
    0.37
     who
    0.35
    åĢij
    0.34
    ìĹIJê²Į
    0.33
    who
    0.31
    ëĭĺ
    0.30
    innen
    0.30
     whom
    0.30
    ship
    0.29
    Activations Density 0.264%

    No Known Activations