© 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. 1113
    Prev
    Next
    INDEX
    Explanations

    was/is + verb/preposition

    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
    è¦ģä¹Ī
    -0.31
     basically
    -0.25
    Overrides
    -0.25
    èĮ«èĮ«
    -0.25
    ablish
    -0.23
     essentially
    -0.23
     Basically
    -0.23
    å°½æĥħ
    -0.22
     nothing
    -0.22
     fulfilled
    -0.22
    POSITIVE LOGITS
     meanwhile
    0.40
     btw
    0.31
     meantime
    0.29
    ä¹Łåľ¨
    0.28
    æĬ¥åijĬæĺ¾ç¤º
    0.25
     also
    0.24
     ÑĤоже
    0.24
     également
    0.24
     unsuccessfully
    0.24
    Aura
    0.24
    Activations Density 0.187%

    No Known Activations