© 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. 837
    Prev
    Next
    INDEX
    Explanations

    reporting on plans or own matters

    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
     Dil
    -0.24
     Bik
    -0.22
     Hub
    -0.22
     initiator
    -0.21
     dilation
    -0.20
    ocytes
    -0.20
    /U
    -0.20
    éļľ
    -0.20
     пÑĢоб
    -0.20
     Burst
    -0.20
    POSITIVE LOGITS
    Own
    0.30
     ÑģвоиÑħ
    0.29
     own
    0.29
     themselves
    0.27
    èĩªèº«çļĦ
    0.27
     própria
    0.27
     próp
    0.27
     Own
    0.26
    èĩªå·±çļĦ
    0.26
    åIJĦèĩª
    0.26
    Activations Density 0.315%

    No Known Activations