© 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. 604
    Prev
    Next
    INDEX
    Explanations

    remaining, other, additional

    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
     classics
    -0.29
    å¥łåŁº
    -0.27
    ç±į
    -0.24
    èµĵ
    -0.24
    enen
    -0.24
    çĽ²
    -0.24
    Mission
    -0.24
    åħ¸åŀĭçļĦ
    -0.24
    è¿Ħä»Ĭ
    -0.24
     Mission
    -0.24
    POSITIVE LOGITS
     remaining
    0.36
    åī©ä½Ļ
    0.32
    remaining
    0.32
    åıªåī©
    0.29
     Remaining
    0.28
    åī©ä¸ĭ
    0.28
    åı¦ä¸ĢåįĬ
    0.28
    loon
    0.27
    åī©
    0.27
    åī©ä¸ĭçļĦ
    0.26
    Activations Density 0.005%

    No Known Activations