© 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. 947
    Prev
    Next
    INDEX
    Explanations

    are not, is not

    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
     Rep
    -0.22
     concluding
    -0.22
     reconsider
    -0.22
    TRY
    -0.22
    丰
    -0.21
     undertaking
    -0.21
    æĥĬåĸľ
    -0.21
     Jud
    -0.21
    åIJİèĢħ
    -0.21
    _up
    -0.21
    POSITIVE LOGITS
     itself
    0.41
    æľ¬èº«
    0.40
    æľ¬èº«çļĦ
    0.28
    æľ¬èº«å°±
    0.28
     themselves
    0.26
     herself
    0.25
     himself
    0.25
    æľ¬èº«å°±æĺ¯
    0.25
     actually
    0.24
    ä¹Łæľī
    0.24
    Activations Density 0.174%

    No Known Activations