© 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. 2117
    Prev
    Next
    INDEX
    Explanations

    TED Talks and National Geographic

    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
    лев
    -0.27
    çľģåĨħ
    -0.26
     Colonial
    -0.24
     statewide
    -0.24
    è¢Ĥ
    -0.24
     duties
    -0.24
    订åįķ
    -0.23
     landlord
    -0.23
     raid
    -0.23
     Attach
    -0.23
    POSITIVE LOGITS
     TED
    0.49
    TED
    0.43
    ç§ijåŃ¦å®¶
    0.34
    æ¼Ķ讲
    0.32
     inspiring
    0.31
     biom
    0.30
    åĵ²åѦ
    0.29
    çĶŁåij½
    0.29
     Nobel
    0.29
     thinkers
    0.29
    Activations Density 0.019%

    No Known Activations