© 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. 564
    Prev
    Next
    INDEX
    Explanations

    -er, -ator, -ener words

    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
    ä¸ĢæŶ
    -0.26
    Handled
    -0.25
    ewise
    -0.24
    Translated
    -0.23
    visibility
    -0.23
     Institutes
    -0.23
    代è¨Ģ
    -0.22
    ivor
    -0.21
    Equality
    -0.21
    åĦ¿
    -0.21
    POSITIVE LOGITS
     capable
    0.31
    -upper
    0.26
     designed
    0.26
     tool
    0.25
     пÑĢедназнаÑĩен
    0.24
     capabilities
    0.24
    忤
    0.24
     devised
    0.24
     capability
    0.24
    åĬŁèĥ½
    0.23
    Activations Density 0.361%

    No Known Activations